Add new Mintlify documentation site (docs_new/) (#23001)
Co-authored-by: AdityaVKochar <adityavardhankochar@gmail.com> Co-authored-by: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com> Co-authored-by: adhyan-jain <adhyanjain2006@gmail.com> Co-authored-by: Adhyan Jain <71976554+adhyan-jain@users.noreply.github.com> Co-authored-by: Maitri-shah29 <maitrirajivshah@gmail.com> Co-authored-by: Adarsh Shirawalmath <114558126+adarshxs@users.noreply.github.com> Co-authored-by: Maitri Shah <shah29maitri@gmail.com> Co-authored-by: Aditya Vardhan Kochar <80113212+AdityaVKochar@users.noreply.github.com> Co-authored-by: Rishit Shivam <164783543+pokymono@users.noreply.github.com> Co-authored-by: Rishitshivam <164783543+Rishitshivam@users.noreply.github.com> Co-authored-by: IshhanKheria <ishhankheria06@gmail.com> Co-authored-by: Ishita Joshi <ishitata.joshi@gmail.com> Co-authored-by: Richard Chen <104477092+Richardczl98@users.noreply.github.com> Co-authored-by: longGGGGGG <553746008@qq.com> Co-authored-by: Richard <richardchen@radixark.ai> Co-authored-by: Nakul Sinha <nakul.new4socials@gmail.com> Co-authored-by: Divyam Agrawal <ludicrouslytrue@gmail.com> Co-authored-by: Richardczl98 <Zhenlinc@stanford.edu> Co-authored-by: Krishang Zinzuwadia <krishangzinzuwadia@gmail.com> Co-authored-by: nimeshas <nimesha.s106@gmail.com> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> Co-authored-by: Jignas Paturu <86356085+JignasP@users.noreply.github.com> Co-authored-by: zijiexia <37504505+zijiexia@users.noreply.github.com>
This commit is contained in:
Mingyi
co-authored by
AdityaVKochar
mintlify[bot]
adhyan-jain
Adhyan Jain
Maitri-shah29
Adarsh Shirawalmath
Maitri Shah
Aditya Vardhan Kochar
Rishit Shivam
Rishitshivam
IshhanKheria
Ishita Joshi
Richard Chen
longGGGGGG
Richard
Nakul Sinha
Divyam Agrawal
Richardczl98
Krishang Zinzuwadia
nimeshas
Claude Opus 4.6
github-actions[bot]
Jignas Paturu
zijiexia
AdityaVKochar
mintlify[bot]
adhyan-jain
Adhyan Jain
Maitri-shah29
Adarsh Shirawalmath
Maitri Shah
Aditya Vardhan Kochar
Rishit Shivam
Rishitshivam
IshhanKheria
Ishita Joshi
Richard Chen
longGGGGGG
Richard
Nakul Sinha
Divyam Agrawal
Richardczl98
Krishang Zinzuwadia
nimeshas
Claude Opus 4.6
github-actions[bot]
Jignas Paturu
zijiexia
parent
575fdc2c4c
commit
a3291b5654
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,309 @@
|
||||
## Running DeepSeek-V3
|
||||
|
||||
### Running DeepSeek in PD mixed mode on 1 x Atlas 800I A3
|
||||
|
||||
W4A8 Model weights could be found [here](https://modelers.cn/models/Modelers_Park/DeepSeek-R1-0528-w4a8).
|
||||
|
||||
<CodeGroup>
|
||||
```shell Launch Server
|
||||
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
|
||||
export STREAMS_PER_DEVICE=32
|
||||
|
||||
#Deepep communication settings
|
||||
export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
|
||||
export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=32
|
||||
export HCCL_BUFFSIZE=1600
|
||||
|
||||
#spec overlap
|
||||
export SGLANG_ENABLE_SPEC_V2=1
|
||||
export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
|
||||
|
||||
#npu acceleration operator
|
||||
export SGLANG_NPU_USE_MLAPO=1
|
||||
export SGLANG_USE_FIA_NZ=1
|
||||
|
||||
python3 -m sglang.launch_server \
|
||||
--model-path ${MODEL_PATH} \
|
||||
--tp 16 \
|
||||
--trust-remote-code \
|
||||
--attention-backend ascend \
|
||||
--device npu \
|
||||
--quantization modelslim \
|
||||
--watchdog-timeout 9000 \
|
||||
--cuda-graph-bs 8 16 24 28 32 \
|
||||
--mem-fraction-static 0.68 \
|
||||
--max-running-requests 128 \
|
||||
--context-length 8188 \
|
||||
--disable-radix-cache \
|
||||
--chunked-prefill-size -1 \
|
||||
--max-prefill-tokens 16384 \
|
||||
--moe-a2a-backend deepep \
|
||||
--deepep-mode auto \
|
||||
--enable-dp-attention \
|
||||
--dp-size 4 \
|
||||
--enable-dp-lm-head \
|
||||
--speculative-algorithm NEXTN \
|
||||
--speculative-num-steps 3 \
|
||||
--speculative-eagle-topk 1 \
|
||||
--speculative-num-draft-tokens 4 \
|
||||
--dtype bfloat16
|
||||
```
|
||||
</CodeGroup>
|
||||
|
||||
### Running DeepSeek with PD disaggregation mode on 2 x Atlas 800I A3
|
||||
|
||||
W4A8 Model weights could be found [here](https://modelers.cn/models/Modelers_Park/DeepSeek-R1-0528-w4a8).
|
||||
|
||||
<Tabs>
|
||||
<Tab title="Prefill">
|
||||
```shell Command
|
||||
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
|
||||
export STREAMS_PER_DEVICE=32
|
||||
|
||||
#memfabric config store
|
||||
export ASCEND_MF_STORE_URL="tcp://<PREFILL_HOST_IP>:<PORT>"
|
||||
|
||||
#Deepep communication settings
|
||||
export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
|
||||
export HCCL_BUFFSIZE=1536
|
||||
|
||||
#npu acceleration operator
|
||||
export SGLANG_NPU_USE_MLAPO=1
|
||||
export SGLANG_USE_FIA_NZ=1
|
||||
export TASK_QUEUE_ENABLE=2
|
||||
|
||||
python -m sglang.launch_server \
|
||||
--model-path ${MODEL_PATH} \
|
||||
--host $PREFILL_HOST_IP \
|
||||
--port 8000 \
|
||||
--disaggregation-mode prefill \
|
||||
--disaggregation-bootstrap-port 8996 \
|
||||
--disaggregation-transfer-backend ascend \
|
||||
--trust-remote-code \
|
||||
--nnodes 1 \
|
||||
--node-rank 0 \
|
||||
--tp-size 16 \
|
||||
--mem-fraction-static 0.6 \
|
||||
--attention-backend ascend \
|
||||
--device npu \
|
||||
--quantization modelslim \
|
||||
--load-balance-method round_robin \
|
||||
--max-running-requests 8 \
|
||||
--context-length 8192 \
|
||||
--disable-radix-cache \
|
||||
--chunked-prefill-size -1 \
|
||||
--max-prefill-tokens 28680 \
|
||||
--moe-a2a-backend deepep \
|
||||
--deepep-mode normal \
|
||||
--speculative-algorithm NEXTN \
|
||||
--speculative-num-steps 3 \
|
||||
--speculative-eagle-topk 1 \
|
||||
--speculative-num-draft-tokens 4 \
|
||||
--dp-size 2 \
|
||||
--enable-dp-attention \
|
||||
--disable-shared-experts-fusion \
|
||||
--dtype bfloat16
|
||||
```
|
||||
|
||||
</Tab>
|
||||
|
||||
<Tab title="Decode">
|
||||
```shell Command
|
||||
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
|
||||
export STREAMS_PER_DEVICE=32
|
||||
|
||||
#memfabric config store
|
||||
export ASCEND_MF_STORE_URL="tcp://<PREFILL_HOST_IP>:<PORT>"
|
||||
|
||||
#Deepep communication settings
|
||||
export HCCL_BUFFSIZE=720
|
||||
export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=88
|
||||
|
||||
#spec overlap
|
||||
export SGLANG_ENABLE_SPEC_V2=1
|
||||
export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
|
||||
|
||||
#npu acceleration operator
|
||||
unset TASK_QUEUE_ENABLE
|
||||
export SGLANG_NPU_USE_MLAPO=1
|
||||
export SGLANG_USE_FIA_NZ=1
|
||||
export ENABLE_MOE_NZ=1
|
||||
|
||||
# suggest max-running-requests <= max-cuda-graph-bs * dp_size, Because when this value is exceeded, performance will significantly degrade.
|
||||
python -m sglang.launch_server \
|
||||
--model-path ${MODEL_PATH} \
|
||||
--disaggregation-mode decode \
|
||||
--host $DECODE_HOST_IP \
|
||||
--port 8001 \
|
||||
--trust-remote-code \
|
||||
--nnodes 1 \
|
||||
--node-rank 0 \
|
||||
--tp-size 16 \
|
||||
--dp-size 16 \
|
||||
--mem-fraction-static 0.8 \
|
||||
--max-running-requests 352 \
|
||||
--attention-backend ascend \
|
||||
--device npu \
|
||||
--quantization modelslim \
|
||||
--prefill-round-robin-balance \
|
||||
--moe-a2a-backend deepep \
|
||||
--enable-dp-attention \
|
||||
--deepep-mode low_latency \
|
||||
--enable-dp-lm-head \
|
||||
--cuda-graph-bs 8 10 12 14 16 18 20 22 \
|
||||
--disaggregation-transfer-backend ascend \
|
||||
--watchdog-timeout 9000 \
|
||||
--context-length 8192 \
|
||||
--speculative-algorithm NEXTN \
|
||||
--speculative-num-steps 3 \
|
||||
--speculative-eagle-topk 1 \
|
||||
--speculative-num-draft-tokens 4 \
|
||||
--disable-shared-experts-fusion \
|
||||
--dtype bfloat16 \
|
||||
--tokenizer-worker-num 4
|
||||
```
|
||||
|
||||
</Tab>
|
||||
|
||||
<Tab title="Router">
|
||||
```shell Command
|
||||
python -m sglang_router.launch_router \
|
||||
--pd-disaggregation \
|
||||
--policy cache_aware \
|
||||
--prefill http://<PREFILL_HOST_IP>:8000 8996 \
|
||||
--decode http://<DECODE_HOST_IP>:8001 \
|
||||
--host 127.0.0.1 \
|
||||
--port 6688
|
||||
```
|
||||
</Tab>
|
||||
</Tabs>
|
||||
|
||||
### Running DeepSeek with PD disaggregation on 4 x Atlas 800I A3
|
||||
|
||||
W8A8 Model weights could be found [here](https://modelers.cn/models/State_Cloud/Deepseek-R1-bf16-hfd-w8a8).
|
||||
|
||||
<Tabs>
|
||||
<Tab title="Prefill & Decode">
|
||||
```shell Command
|
||||
echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
|
||||
sysctl -w vm.swappiness=0
|
||||
sysctl -w kernel.numa_balancing=0
|
||||
sysctl -w kernel.sched_migration_cost_ns=50000
|
||||
export SGLANG_SET_CPU_AFFINITY=1
|
||||
unset ASCEND_LAUNCH_BLOCKING
|
||||
source /usr/local/Ascend/ascend-toolkit/set_env.sh
|
||||
source /usr/local/Ascend/nnal/atb/set_env.sh
|
||||
export PATH=/usr/local/Ascend/8.5.0/compiler/bishengir/bin:$PATH
|
||||
|
||||
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
|
||||
export STREAMS_PER_DEVICE=32
|
||||
|
||||
export ASCEND_MF_STORE_URL="tcp://your prefill ip1:24669"
|
||||
|
||||
P_IP=('your prefill ip1' 'your prefill ip2')
|
||||
|
||||
D_IP=('your decode ip1' 'your decode ip2')
|
||||
|
||||
MODEL_PATH=xxx
|
||||
|
||||
export SGLANG_NPU_USE_MLAPO=1
|
||||
export SGLANG_USE_FIA_NZ=1
|
||||
|
||||
LOCAL_HOST1=`hostname -I|awk -F " " '{print$1}'`
|
||||
LOCAL_HOST2=`hostname -I|awk -F " " '{print$2}'`
|
||||
echo "${LOCAL_HOST1}"
|
||||
echo "${LOCAL_HOST2}"
|
||||
# prefill
|
||||
for i in "${!P_IP[@]}";
|
||||
do
|
||||
if [[ "$LOCAL_HOST1" == "${P_IP[$i]}" || "$LOCAL_HOST2" == "${P_IP[$i]}" ]];
|
||||
then
|
||||
echo "${P_IP[$i]}"
|
||||
export HCCL_BUFFSIZE=1536
|
||||
export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
|
||||
export TASK_QUEUE_ENABLE=2
|
||||
|
||||
export HCCL_SOCKET_IFNAME=lo
|
||||
export GLOO_SOCKET_IFNAME=lo
|
||||
python -m sglang.launch_server --model-path ${MODEL_PATH} --disaggregation-mode prefill --host ${P_IP[$i]} \
|
||||
--port 8000 --disaggregation-bootstrap-port $((8998+$i)) --trust-remote-code --nnodes 1 --node-rank 0 \
|
||||
--tp-size 16 --mem-fraction-static 0.81 --attention-backend ascend --device npu --quantization modelslim \
|
||||
--disaggregation-transfer-backend ascend --max-running-requests 8 --context-length 8192 --disable-radix-cache \
|
||||
--chunked-prefill-size -1 --max-prefill-tokens 28680 --moe-a2a-backend deepep --deepep-mode normal \
|
||||
--speculative-algorithm NEXTN --speculative-num-steps 1 --speculative-eagle-topk 1 --speculative-num-draft-tokens 2 \
|
||||
--dp-size 2 --enable-dp-attention --disable-shared-experts-fusion --dtype bfloat16 --enable-attn-tp-input-scattered
|
||||
NODE_RANK=$i
|
||||
break
|
||||
fi
|
||||
done
|
||||
|
||||
# decode
|
||||
for i in "${!D_IP[@]}";
|
||||
do
|
||||
if [[ "$LOCAL_HOST1" == "${D_IP[$i]}" || "$LOCAL_HOST2" == "${D_IP[$i]}" ]];
|
||||
then
|
||||
echo "${D_IP[$i]}"
|
||||
export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
|
||||
export SGLANG_ENABLE_SPEC_V2=1
|
||||
export HCCL_BUFFSIZE=650
|
||||
export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=78
|
||||
export TASK_QUEUE_ENABLE=1
|
||||
export SGLANG_SCHEDULER_SKIP_ALL_GATHER=1
|
||||
export HCCL_SOCKET_IFNAME=xxx
|
||||
export GLOO_SOCKET_IFNAME=xxx
|
||||
python -m sglang.launch_server --model-path ${MODEL_PATH} --disaggregation-mode decode --host ${D_IP[$i]} \
|
||||
--port 8001 --trust-remote-code --dist-init-addr ${D_IP[0]}:5000 --nnodes 2 --node-rank $i --tp-size 32 --dp-size 32 \
|
||||
--mem-fraction-static 0.815 --max-running-requests 832 --attention-backend ascend --device npu --quantization modelslim \
|
||||
--moe-a2a-backend deepep --enable-dp-attention --deepep-mode low_latency --enable-dp-lm-head --moe-dense-tp 1 \
|
||||
--cuda-graph-bs 12 14 16 18 20 22 24 26 --disaggregation-transfer-backend ascend --watchdog-timeout 9000 --context-length 8192 \
|
||||
--speculative-algorithm NEXTN --speculative-num-steps 2 --speculative-eagle-topk 1 --speculative-num-draft-tokens 3 \
|
||||
--tokenizer-worker-num 4 --prefill-round-robin-balance --disable-shared-experts-fusion --dtype bfloat16 \
|
||||
--load-balance-method decode_round_robin
|
||||
NODE_RANK=$i
|
||||
break
|
||||
fi
|
||||
done
|
||||
```
|
||||
|
||||
</Tab>
|
||||
|
||||
<Tab title="Router">
|
||||
```shell Command
|
||||
export SGLANG_DP_ROUND_ROBIN=1
|
||||
python -m sglang_router.launch_router \
|
||||
--pd-disaggregation \
|
||||
--policy cache_aware \
|
||||
--prefill http://P_IP:8000 8998 \
|
||||
--prefill http://P_IP:8000 8999 \
|
||||
--decode http://D_IP:8001 \
|
||||
--host 127.0.0.1 \
|
||||
--port 6688 \
|
||||
--mini-lb
|
||||
```
|
||||
</Tab>
|
||||
</Tabs>
|
||||
|
||||
### Test GSM8K
|
||||
|
||||
<CodeGroup>
|
||||
```python Test GSM8K
|
||||
from types import SimpleNamespace
|
||||
from sglang.test.few_shot_gsm8k import run_eval
|
||||
|
||||
def gsm8k():
|
||||
args = SimpleNamespace(
|
||||
num_shots=5,
|
||||
data_path=None,
|
||||
num_questions=200,
|
||||
max_new_tokens=512,
|
||||
parallel=32,
|
||||
host=f"http://127.0.0.1",
|
||||
port=6688,
|
||||
)
|
||||
metrics = run_eval(args)
|
||||
print(f"{metrics=}")
|
||||
print(f"{metrics['accuracy']=}")
|
||||
if __name__ == "__main__":
|
||||
gsm8k()
|
||||
```
|
||||
</CodeGroup>
|
||||
@@ -0,0 +1,200 @@
|
||||
## Introduction
|
||||
|
||||
The GLM (General Language Model) series is an open-source bilingual large language model family jointly developed by the KEG Laboratory of Tsinghua University and Zhipu AI. This series of models has performed outstandingly in the field of Chinese NLP with its unique unified pre-training framework and bilingual capabilities. [GLM-5](https://huggingface.co/zai-org/GLM-5) adopts the DeepSeek-V3/V3.2 architecture, including the sparse attention (DSA) and multi-token prediction (MTP). Ascend supports GLM-5 with 0Day based on the SGLang inference framework, achieving low-code seamless enablement and compatibility with the mainstream distributed parallel capabilities within the current SGLang framework. We welcome developers to download and experience it.
|
||||
|
||||
## Environment Preparation
|
||||
|
||||
### Model Weight
|
||||
|
||||
- `GLM-5.0`(BF16 version): [Download model weight](https://www.modelscope.cn/models/ZhipuAI/GLM-5).
|
||||
- `GLM-5.0-w4a8`(Quantized version without mtp): [Download model weight](https://modelers.cn/models/Eco-Tech/GLM-5-w4a8).
|
||||
- You can use [msmodelslim](https://gitcode.com/Ascend/msmodelslim) to quantify the model naively.
|
||||
|
||||
|
||||
### Installation
|
||||
|
||||
The dependencies required for the NPU runtime environment have been integrated into a Docker image and uploaded to the quay.io platform. You can directly pull it.
|
||||
|
||||
<CodeGroup>
|
||||
```bash Pull and Start Container
|
||||
#Atlas 800 A3
|
||||
docker pull swr.cn-southwest-2.myhuaweicloud.com/base_image/dockerhub/lmsysorg/sglang:cann8.5.0-a3-glm5
|
||||
#Atlas 800 A2
|
||||
docker pull swr.cn-southwest-2.myhuaweicloud.com/base_image/dockerhub/lmsysorg/sglang:cann8.5.0-910b-glm5
|
||||
|
||||
#start container
|
||||
docker run -itd --shm-size=16g --privileged=true --name ${NAME} \
|
||||
--privileged=true --net=host \
|
||||
-v /var/queue_schedule:/var/queue_schedule \
|
||||
-v /etc/ascend_install.info:/etc/ascend_install.info \
|
||||
-v /usr/local/sbin:/usr/local/sbin \
|
||||
-v /usr/local/Ascend/driver:/usr/local/Ascend/driver \
|
||||
-v /usr/local/Ascend/firmware:/usr/local/Ascend/firmware \
|
||||
--device=/dev/davinci0:/dev/davinci0 \
|
||||
--device=/dev/davinci1:/dev/avinci1 \
|
||||
--device=/dev/davinci2:/dev/davinci2 \
|
||||
--device=/dev/davinci3:/dev/davinci3 \
|
||||
--device=/dev/davinci4:/dev/davinci4 \
|
||||
--device=/dev/davinci5:/dev/davinci5 \
|
||||
--device=/dev/davinci6:/dev/davinci6 \
|
||||
--device=/dev/davinci7:/dev/davinci7 \
|
||||
--device=/dev/davinci8:/dev/davinci8 \
|
||||
--device=/dev/davinci9:/dev/davinci9 \
|
||||
--device=/dev/davinci10:/dev/davinci10 \
|
||||
--device=/dev/davinci11:/dev/davinci11 \
|
||||
--device=/dev/davinci12:/dev/davinci12 \
|
||||
--device=/dev/davinci13:/dev/davinci13 \
|
||||
--device=/dev/davinci14:/dev/davinci14 \
|
||||
--device=/dev/davinci15:/dev/davinci15 \
|
||||
--device=/dev/davinci_manager:/dev/davinci_manager \
|
||||
--device=/dev/hisi_hdc:/dev/hisi_hdc \
|
||||
--entrypoint=bash \
|
||||
swr.cn-southwest-2.myhuaweicloud.com/base_image/dockerhub/lmsysorg/sglang:${TAG}
|
||||
```
|
||||
</CodeGroup>
|
||||
|
||||
Note: Using this image, you need to update transformers to main branch
|
||||
<CodeGroup>
|
||||
```shell Update Transformers
|
||||
# reinstall transformers
|
||||
pip install git+https://github.com/huggingface/transformers.git
|
||||
```
|
||||
</CodeGroup>
|
||||
|
||||
## Deployment
|
||||
|
||||
### Single-node Deployment
|
||||
|
||||
- Quantized model `glm5_w4a8` can be deployed on 1 Atlas 800 A3 (64G × 16) .
|
||||
|
||||
Run the following script to execute online inference.
|
||||
|
||||
<CodeGroup>
|
||||
```shell Launch Server
|
||||
# high performance cpu
|
||||
echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
|
||||
sysctl -w vm.swappiness=0
|
||||
sysctl -w kernel.numa_balancing=0
|
||||
sysctl -w kernel.sched_migration_cost_ns=50000
|
||||
# bind cpu
|
||||
export SGLANG_SET_CPU_AFFINITY=1
|
||||
|
||||
unset https_proxy
|
||||
unset http_proxy
|
||||
unset HTTPS_PROXY
|
||||
unset HTTP_PROXY
|
||||
unset ASCEND_LAUNCH_BLOCKING
|
||||
# cann
|
||||
source /usr/local/Ascend/ascend-toolkit/set_env.sh
|
||||
source /usr/local/Ascend/nnal/atb/set_env.sh
|
||||
|
||||
export STREAMS_PER_DEVICE=32
|
||||
export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=600
|
||||
export SGLANG_ENABLE_SPEC_V2=1
|
||||
export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
|
||||
export SGLANG_NPU_USE_MULTI_STREAM=1
|
||||
export HCCL_BUFFSIZE=1000
|
||||
export HCCL_OP_EXPANSION_MODE=AIV
|
||||
export HCCL_SOCKET_IFNAME=lo
|
||||
export GLOO_SOCKET_IFNAME=lo
|
||||
|
||||
python3 -m sglang.launch_server \
|
||||
--model-path $MODEL_PATH \
|
||||
--attention-backend ascend \
|
||||
--device npu \
|
||||
--tp-size 16 --nnodes 1 --node-rank 0 \
|
||||
--chunked-prefill-size 16384 --max-prefill-tokens 280000 \
|
||||
--trust-remote-code \
|
||||
--host 127.0.0.1 \
|
||||
--mem-fraction-static 0.7 \
|
||||
--port 8000 \
|
||||
--served-model-name glm-5 \
|
||||
--cuda-graph-bs 16 \
|
||||
--quantization modelslim \
|
||||
--moe-a2a-backend deepep --deepep-mode auto
|
||||
```
|
||||
</CodeGroup>
|
||||
|
||||
### Multi-node Deployment
|
||||
|
||||
- `GLM-5-bf16`: require at least 2 Atlas 800 A3 (64G × 16).
|
||||
|
||||
**A3 series**
|
||||
|
||||
Modify the IP of 2 nodes, then run the same scripts on two nodes.
|
||||
|
||||
**node 0/1**
|
||||
|
||||
<CodeGroup>
|
||||
```shell Launch Multi-node Server
|
||||
echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
|
||||
sysctl -w vm.swappiness=0
|
||||
sysctl -w kernel.numa_balancing=0
|
||||
sysctl -w kernel.sched_migration_cost_ns=50000
|
||||
# bind cpu
|
||||
export SGLANG_SET_CPU_AFFINITY=1
|
||||
|
||||
unset https_proxy
|
||||
unset http_proxy
|
||||
unset HTTPS_PROXY
|
||||
unset HTTP_PROXY
|
||||
unset ASCEND_LAUNCH_BLOCKING
|
||||
# cann
|
||||
source /usr/local/Ascend/ascend-toolkit/set_env.sh
|
||||
source /usr/local/Ascend/nnal/atb/set_env.sh
|
||||
|
||||
export STREAMS_PER_DEVICE=32
|
||||
export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=600
|
||||
export SGLANG_ENABLE_SPEC_V2=1
|
||||
export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
|
||||
export SGLANG_NPU_USE_MULTI_STREAM=1
|
||||
export HCCL_BUFFSIZE=1000
|
||||
export HCCL_OP_EXPANSION_MODE=AIV
|
||||
|
||||
# Run command ifconfig on two nodes, find out which inet addr has same IP with your node IP. That is your public interface, which should be added here
|
||||
export HCCL_SOCKET_IFNAME=lo
|
||||
export GLOO_SOCKET_IFNAME=lo
|
||||
|
||||
|
||||
P_IP=('your ip1' 'your ip2')
|
||||
P_MASTER="${P_IP[0]}:your port"
|
||||
export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=600
|
||||
|
||||
export SGLANG_ENABLE_SPEC_V2=1
|
||||
export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
|
||||
|
||||
LOCAL_HOST1=`hostname -I|awk -F " " '{print$1}'`
|
||||
LOCAL_HOST2=`hostname -I|awk -F " " '{print$2}'`
|
||||
for i in "${!P_IP[@]}";
|
||||
do
|
||||
if [[ "$LOCAL_HOST1" == "${P_IP[$i]}" || "$LOCAL_HOST2" == "${P_IP[$i]}" ]];
|
||||
then
|
||||
echo "${P_IP[$i]}"
|
||||
python3 -m sglang.launch_server \
|
||||
--model-path $MODEL_PATH \
|
||||
--attention-backend ascend \
|
||||
--device npu \
|
||||
--tp-size 32 --nnodes 2 --node-rank $i --dist-init-addr $P_MASTER \
|
||||
--chunked-prefill-size 16384 --max-prefill-tokens 131072 \
|
||||
--trust-remote-code \
|
||||
--host 127.0.0.1 \
|
||||
--mem-fraction-static 0.8\
|
||||
--port 8000 \
|
||||
--served-model-name glm-5 \
|
||||
--cuda-graph-max-bs 16 \
|
||||
--disable-radix-cache
|
||||
NODE_RANK=$i
|
||||
break
|
||||
fi
|
||||
done
|
||||
|
||||
```
|
||||
</CodeGroup>
|
||||
|
||||
### Prefill-Decode Disaggregation
|
||||
|
||||
Not test yet.
|
||||
|
||||
### Using Benchmark
|
||||
|
||||
Refer to [Benchmark and Profiling](../../developer_guide/benchmark_and_profiling) for details.
|
||||
@@ -0,0 +1,169 @@
|
||||
## Introduction
|
||||
|
||||
MindSpore is a high-performance AI framework optimized for Ascend NPUs. This doc guides users to run MindSpore models in SGLang.
|
||||
|
||||
## Requirements
|
||||
|
||||
MindSpore currently only supports Ascend NPU devices. Users need to first install Ascend CANN software packages.
|
||||
The CANN software packages can be downloaded from the [Ascend Official Website](https://www.hiascend.com). The recommended version is 8.3.RC2.
|
||||
|
||||
## Supported Models
|
||||
|
||||
Currently, the following models are supported:
|
||||
|
||||
- **Qwen3**: Dense and MoE models
|
||||
- **DeepSeek V3/R1**
|
||||
- *More models coming soon...*
|
||||
|
||||
## Installation
|
||||
|
||||
<Note>
|
||||
Currently, MindSpore models are provided by an independent package `sgl-mindspore`. Support for MindSpore is built upon current SGLang support for Ascend NPU platform. Please first [install SGLang for Ascend NPU](./SGLang-installation-with-NPUs-support) and then install `sgl-mindspore`:
|
||||
</Note>
|
||||
|
||||
<CodeGroup>
|
||||
```shell Install
|
||||
git clone https://github.com/mindspore-lab/sgl-mindspore.git
|
||||
cd sgl-mindspore
|
||||
pip install -e .
|
||||
```
|
||||
</CodeGroup>
|
||||
|
||||
|
||||
## Run Model
|
||||
|
||||
Current SGLang-MindSpore supports Qwen3 and DeepSeek V3/R1 models. This doc uses Qwen3-8B as an example.
|
||||
|
||||
### Offline infer
|
||||
|
||||
Use the following script for offline infer:
|
||||
|
||||
<CodeGroup>
|
||||
```python Offline Inference
|
||||
import sglang as sgl
|
||||
|
||||
# Initialize the engine with MindSpore backend
|
||||
llm = sgl.Engine(
|
||||
model_path="/path/to/your/model", # Local model path
|
||||
device="npu", # Use NPU device
|
||||
model_impl="mindspore", # MindSpore implementation
|
||||
attention_backend="ascend", # Attention backend
|
||||
tp_size=1, # Tensor parallelism size
|
||||
dp_size=1 # Data parallelism size
|
||||
)
|
||||
|
||||
# Generate text
|
||||
prompts = [
|
||||
"Hello, my name is",
|
||||
"The capital of France is",
|
||||
"The future of AI is"
|
||||
]
|
||||
|
||||
sampling_params = {"temperature": 0, "top_p": 0.9}
|
||||
outputs = llm.generate(prompts, sampling_params)
|
||||
|
||||
for prompt, output in zip(prompts, outputs):
|
||||
print(f"Prompt: {prompt}")
|
||||
print(f"Generated: {output['text']}")
|
||||
print("---")
|
||||
```
|
||||
</CodeGroup>
|
||||
|
||||
### Start server
|
||||
|
||||
Launch a server with MindSpore backend:
|
||||
|
||||
<CodeGroup>
|
||||
```bash Launch Server
|
||||
# Basic server startup
|
||||
python3 -m sglang.launch_server \
|
||||
--model-path /path/to/your/model \
|
||||
--host 0.0.0.0 \
|
||||
--device npu \
|
||||
--model-impl mindspore \
|
||||
--attention-backend ascend \
|
||||
--tp-size 1 \
|
||||
--dp-size 1
|
||||
```
|
||||
</CodeGroup>
|
||||
|
||||
For distributed server with multiple nodes:
|
||||
|
||||
<CodeGroup>
|
||||
```bash Multi-node Distributed
|
||||
# Multi-node distributed server
|
||||
python3 -m sglang.launch_server \
|
||||
--model-path /path/to/your/model \
|
||||
--host 0.0.0.0 \
|
||||
--device npu \
|
||||
--model-impl mindspore \
|
||||
--attention-backend ascend \
|
||||
--dist-init-addr 127.0.0.1:29500 \
|
||||
--nnodes 2 \
|
||||
--node-rank 0 \
|
||||
--tp-size 4 \
|
||||
--dp-size 2
|
||||
```
|
||||
</CodeGroup>
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
#### Debug Mode
|
||||
|
||||
Enable sglang debug logging by log-level argument.
|
||||
|
||||
<CodeGroup>
|
||||
```bash Debug Mode
|
||||
python3 -m sglang.launch_server \
|
||||
--model-path /path/to/your/model \
|
||||
--host 0.0.0.0 \
|
||||
--device npu \
|
||||
--model-impl mindspore \
|
||||
--attention-backend ascend \
|
||||
--log-level DEBUG
|
||||
```
|
||||
</CodeGroup>
|
||||
|
||||
Enable mindspore info and debug logging by setting environments.
|
||||
|
||||
<CodeGroup>
|
||||
```bash Set Log Level
|
||||
export GLOG_v=1 # INFO
|
||||
export GLOG_v=0 # DEBUG
|
||||
```
|
||||
</CodeGroup>
|
||||
|
||||
#### Explicitly select devices
|
||||
|
||||
Use the following environment variable to explicitly select the devices to use.
|
||||
|
||||
<CodeGroup>
|
||||
```shell Select Devices
|
||||
export ASCEND_RT_VISIBLE_DEVICES=4,5,6,7 # to set device
|
||||
```
|
||||
</CodeGroup>
|
||||
|
||||
#### Some communication environment issues
|
||||
|
||||
In case of some environment with special communication environment, users need set some environment variables.
|
||||
|
||||
<CodeGroup>
|
||||
```shell Disable LCCL
|
||||
export MS_ENABLE_LCCL=off # current not support LCCL communication mode in SGLang-MindSpore
|
||||
```
|
||||
</CodeGroup>
|
||||
|
||||
#### Some dependencies of protobuf
|
||||
|
||||
In case of some environment with special protobuf version, users need set some environment variables to avoid binary version mismatch.
|
||||
|
||||
<CodeGroup>
|
||||
```shell Fix Protobuf
|
||||
export PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python # to avoid protobuf binary version mismatch
|
||||
```
|
||||
</CodeGroup>
|
||||
|
||||
## Support
|
||||
For MindSpore-specific issues:
|
||||
|
||||
- Refer to the [MindSpore documentation](https://www.mindspore.cn/)
|
||||
@@ -0,0 +1,124 @@
|
||||
## Running Qwen3
|
||||
|
||||
### Running Qwen3-32B on 1 x Atlas 800I A3
|
||||
|
||||
Model weights could be found [here](https://huggingface.co/Qwen/Qwen3-32B)
|
||||
|
||||
<CodeGroup>
|
||||
```shell Launch Server
|
||||
export SGLANG_SET_CPU_AFFINITY=1
|
||||
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
|
||||
export STREAMS_PER_DEVICE=32
|
||||
export HCCL_BUFFSIZE=1536
|
||||
export HCCL_OP_EXPANSION_MODE=AIV
|
||||
|
||||
python -m sglang.launch_server \
|
||||
--device npu \
|
||||
--attention-backend ascend \
|
||||
--trust-remote-code \
|
||||
--tp-size 4 \
|
||||
--model-path Qwen/Qwen3-32B \
|
||||
--mem-fraction-static 0.8
|
||||
```
|
||||
</CodeGroup>
|
||||
|
||||
### Running Qwen3-32B on 1 x Atlas 800I A3 with Qwen3-32B-Eagle3
|
||||
|
||||
Model weights could be found [here](https://huggingface.co/Qwen/Qwen3-32B)
|
||||
|
||||
Speculative model weights could be found [here](https://huggingface.co/Zhihu-ai/Zhi-Create-Qwen3-32B-Eagle3)
|
||||
|
||||
<CodeGroup>
|
||||
```shell Launch Server with Eagle3
|
||||
export SGLANG_SET_CPU_AFFINITY=1
|
||||
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
|
||||
export STREAMS_PER_DEVICE=32
|
||||
export HCCL_OP_EXPANSION_MODE=AIV
|
||||
export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
|
||||
export SGLANG_ENABLE_SPEC_V2=1
|
||||
|
||||
python -m sglang.launch_server \
|
||||
--device npu \
|
||||
--attention-backend ascend \
|
||||
--trust-remote-code \
|
||||
--tp-size 4 \
|
||||
--model-path Qwen/Qwen3-32B \
|
||||
--mem-fraction-static 0.8 \
|
||||
--speculative-algorithm EAGLE3 \
|
||||
--speculative-draft-model-path Qwen/Qwen3-32B-Eagle3 \
|
||||
--speculative-num-steps 1 \
|
||||
--speculative-eagle-topk 1 \
|
||||
--speculative-num-draft-tokens 2
|
||||
```
|
||||
</CodeGroup>
|
||||
|
||||
### Running Qwen3-30B-A3B MOE on 1 x Atlas 800I A3
|
||||
|
||||
Model weights could be found [here](https://huggingface.co/Qwen/Qwen3-30B-A3B)
|
||||
|
||||
<CodeGroup>
|
||||
```shell Launch Server
|
||||
export SGLANG_SET_CPU_AFFINITY=1
|
||||
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
|
||||
export STREAMS_PER_DEVICE=32
|
||||
export HCCL_BUFFSIZE=1536
|
||||
export HCCL_OP_EXPANSION_MODE=AIV
|
||||
export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=32
|
||||
export SGLANG_DEEPEP_BF16_DISPATCH=1
|
||||
|
||||
python -m sglang.launch_server \
|
||||
--device npu \
|
||||
--attention-backend ascend \
|
||||
--trust-remote-code \
|
||||
--tp-size 4 \
|
||||
--model-path Qwen/Qwen3-30B-A3B \
|
||||
--mem-fraction-static 0.8
|
||||
```
|
||||
</CodeGroup>
|
||||
|
||||
### Running Qwen3-235B-A22B-Instruct-2507 MOE on 1 x Atlas 800I A3
|
||||
|
||||
Model weights could be found [here](https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507)
|
||||
|
||||
<CodeGroup>
|
||||
```shell Launch Server
|
||||
export SGLANG_SET_CPU_AFFINITY=1
|
||||
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
|
||||
export STREAMS_PER_DEVICE=32
|
||||
export HCCL_BUFFSIZE=1536
|
||||
export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=32
|
||||
export SGLANG_DEEPEP_BF16_DISPATCH=1
|
||||
|
||||
python -m sglang.launch_server \
|
||||
--model-path Qwen/Qwen3-235B-A22B-Instruct-2507 \
|
||||
--tp-size 16 \
|
||||
--trust-remote-code \
|
||||
--attention-backend ascend \
|
||||
--device npu \
|
||||
--watchdog-timeout 9000 \
|
||||
--mem-fraction-static 0.8
|
||||
```
|
||||
</CodeGroup>
|
||||
|
||||
### Running Qwen3-VL-8B-Instruct on 1 x Atlas 800I A3
|
||||
|
||||
Model weights could be found [here](https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct)
|
||||
|
||||
<CodeGroup>
|
||||
```shell Launch Server
|
||||
export SGLANG_SET_CPU_AFFINITY=1
|
||||
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
|
||||
export STREAMS_PER_DEVICE=32
|
||||
export HCCL_BUFFSIZE=1536
|
||||
export HCCL_OP_EXPANSION_MODE=AIV
|
||||
|
||||
python -m sglang.launch_server \
|
||||
--enable-multimodal \
|
||||
--attention-backend ascend \
|
||||
--mm-attention-backend ascend_attn \
|
||||
--trust-remote-code \
|
||||
--tp-size 4 \
|
||||
--model-path Qwen/Qwen3-VL-8B-Instruct \
|
||||
--mem-fraction-static 0.8
|
||||
```
|
||||
</CodeGroup>
|
||||
@@ -0,0 +1,106 @@
|
||||
## Environment Preparation
|
||||
|
||||
### Installation
|
||||
|
||||
The dependencies required for the NPU runtime environment have been integrated into a Docker image and uploaded to the quay.io platform. You can directly pull it.
|
||||
|
||||
<CodeGroup>
|
||||
```bash Pull and Start Container
|
||||
#Atlas 800 A3
|
||||
docker pull swr.cn-southwest-2.myhuaweicloud.com/base_image/dockerhub/lmsysorg/sglang:cann8.5.0-a3-qwen3.5
|
||||
#Atlas 800 A2
|
||||
docker pull swr.cn-southwest-2.myhuaweicloud.com/base_image/dockerhub/lmsysorg/sglang:cann8.5.0-910b-qwen3.5
|
||||
|
||||
#start container
|
||||
docker run -itd --shm-size=16g --privileged=true --name ${NAME} \
|
||||
--privileged=true --net=host \
|
||||
-v /var/queue_schedule:/var/queue_schedule \
|
||||
-v /etc/ascend_install.info:/etc/ascend_install.info \
|
||||
-v /usr/local/sbin:/usr/local/sbin \
|
||||
-v /usr/local/Ascend/driver:/usr/local/Ascend/driver \
|
||||
-v /usr/local/Ascend/firmware:/usr/local/Ascend/firmware \
|
||||
--device=/dev/davinci0:/dev/davinci0 \
|
||||
--device=/dev/davinci1:/dev/davinci1 \
|
||||
--device=/dev/davinci2:/dev/davinci2 \
|
||||
--device=/dev/davinci3:/dev/davinci3 \
|
||||
--device=/dev/davinci4:/dev/davinci4 \
|
||||
--device=/dev/davinci5:/dev/davinci5 \
|
||||
--device=/dev/davinci6:/dev/davinci6 \
|
||||
--device=/dev/davinci7:/dev/davinci7 \
|
||||
--device=/dev/davinci8:/dev/davinci8 \
|
||||
--device=/dev/davinci9:/dev/davinci9 \
|
||||
--device=/dev/davinci10:/dev/davinci10 \
|
||||
--device=/dev/davinci11:/dev/davinci11 \
|
||||
--device=/dev/davinci12:/dev/davinci12 \
|
||||
--device=/dev/davinci13:/dev/davinci13 \
|
||||
--device=/dev/davinci14:/dev/davinci14 \
|
||||
--device=/dev/davinci15:/dev/davinci15 \
|
||||
--device=/dev/davinci_manager:/dev/davinci_manager \
|
||||
--device=/dev/hisi_hdc:/dev/hisi_hdc \
|
||||
--entrypoint=bash \
|
||||
swr.cn-southwest-2.myhuaweicloud.com/base_image/dockerhub/lmsysorg/sglang:${TAG}
|
||||
```
|
||||
</CodeGroup>
|
||||
|
||||
## Deployment
|
||||
|
||||
### Single-node Deployment
|
||||
|
||||
- Quantized model `qwen35_w8a8` can be deployed on 1 Atlas 800 A3 (64G × 16) .
|
||||
|
||||
Run the following script to execute online inference.
|
||||
|
||||
<CodeGroup>
|
||||
```shell Launch Server
|
||||
# high performance cpu
|
||||
echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
|
||||
sysctl -w vm.swappiness=0
|
||||
sysctl -w kernel.numa_balancing=0
|
||||
sysctl -w kernel.sched_migration_cost_ns=50000
|
||||
# bind cpu
|
||||
export SGLANG_SET_CPU_AFFINITY=1
|
||||
|
||||
unset https_proxy
|
||||
unset http_proxy
|
||||
unset HTTPS_PROXY
|
||||
unset HTTP_PROXY
|
||||
unset ASCEND_LAUNCH_BLOCKING
|
||||
# cann
|
||||
source /usr/local/Ascend/ascend-toolkit/set_env.sh
|
||||
source /usr/local/Ascend/nnal/atb/set_env.sh
|
||||
|
||||
export STREAMS_PER_DEVICE=32
|
||||
export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=600
|
||||
export SGLANG_ENABLE_SPEC_V2=1
|
||||
export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
|
||||
export SGLANG_NPU_USE_MULTI_STREAM=1
|
||||
export HCCL_BUFFSIZE=1000
|
||||
export HCCL_OP_EXPANSION_MODE=AIV
|
||||
export HCCL_SOCKET_IFNAME=lo
|
||||
export GLOO_SOCKET_IFNAME=lo
|
||||
|
||||
python3 -m sglang.launch_server \
|
||||
--model-path $MODEL_PATH \
|
||||
--attention-backend ascend \
|
||||
--device npu \
|
||||
--tp-size 16 --nnodes 1 --node-rank 0 \
|
||||
--chunked-prefill-size 16384 --max-prefill-tokens 280000 \
|
||||
--trust-remote-code \
|
||||
--host 127.0.0.1 \
|
||||
--mem-fraction-static 0.7 \
|
||||
--port 8000 \
|
||||
--cuda-graph-bs 16 \
|
||||
--quantization modelslim \
|
||||
--enable-multimodal \
|
||||
--mm-attention-backend ascend_attn \
|
||||
--dtype bfloat16
|
||||
```
|
||||
</CodeGroup>
|
||||
|
||||
### Prefill-Decode Disaggregation
|
||||
|
||||
Not test yet.
|
||||
|
||||
### Using Benchmark
|
||||
|
||||
Refer to [Benchmark and Profiling](../../developer_guide/benchmark_and_profiling) for details.
|
||||
+318
@@ -0,0 +1,318 @@
|
||||
---
|
||||
title: SGLang installation with NPUs support
|
||||
---
|
||||
|
||||
You can install SGLang using any of the methods below. Please go through `System Settings` section to ensure the clusters are roaring at max performance. Feel free to leave an issue [here at sglang](https://github.com/sgl-project/sglang/issues) if you encounter any issues or have any problems.
|
||||
|
||||
## Component Version Mapping For SGLang
|
||||
|
||||
<table style={{width: "100%", borderCollapse: "collapse", tableLayout: "fixed"}}>
|
||||
<colgroup>
|
||||
<col style={{width: "34%"}} />
|
||||
<col style={{width: "33%"}} />
|
||||
<col style={{width: "33%"}} />
|
||||
</colgroup>
|
||||
<thead>
|
||||
<tr style={{borderBottom: "2px solid #d55816"}}>
|
||||
<th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.02)"}}>Component</th>
|
||||
<th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.05)"}}>Version</th>
|
||||
<th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.02)"}}>Obtain Way</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>HDK</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>25.3.RC1</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>[<Icon icon="download" />](https://hiascend.com/hardware/firmware-drivers/commercial?product=7\&model=33)</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>CANN</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>8.5.0</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>[Obtain Images](#obtain-cann-image)</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Pytorch Adapter</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>7.3.0</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>[<Icon icon="external-link" />](https://gitcode.com/Ascend/pytorch/releases)</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>MemFabric</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>1.0.5</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`pip install memfabric-hybrid==1.0.5`</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Triton</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>3.2.0</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`pip install triton-ascend`</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Bisheng</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>20251121</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>[<Icon icon="external-link" />](https://sglang-ascend.obs.cn-east-3.myhuaweicloud.com/sglang/triton_ascend/Ascend-BiSheng-toolkit_aarch64_20251121.run)</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>SGLang NPU Kernel</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>NA</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>[<Icon icon="external-link" />](https://github.com/sgl-project/sgl-kernel-npu/releases)</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
<Accordion title="Obtain CANN Image" defaultOpen="true">
|
||||
|
||||
You can obtain the dependency of a specified version of CANN through an image.
|
||||
|
||||
```bash
|
||||
# for Atlas 800I A3 and Ubuntu OS
|
||||
docker pull quay.io/ascend/cann:8.5.0-a3-ubuntu22.04-py3.11
|
||||
# for Atlas 800I A2 and Ubuntu OS
|
||||
docker pull quay.io/ascend/cann:8.5.0-910b-ubuntu22.04-py3.11
|
||||
```
|
||||
</Accordion>
|
||||
|
||||
## Preparing the Running Environment
|
||||
|
||||
<Tabs>
|
||||
<Tab title="Source">
|
||||
<AccordionGroup>
|
||||
<Accordion title="Python Version">
|
||||
Only `python==3.11` is supported currently. If you don't want to break system pre-installed python, try installing with [conda](https://github.com/conda/conda).
|
||||
|
||||
```bash
|
||||
conda create --name sglang_npu python=3.11
|
||||
conda activate sglang_npu
|
||||
```
|
||||
</Accordion>
|
||||
<Accordion title="CANN">
|
||||
Prior to start work with SGLang on Ascend you need to install CANN Toolkit, Kernels operator package and NNAL version 8.3.RC2 or higher, check the [installation guide](https://www.hiascend.com/document/detail/zh/CANNCommunityEdition/83RC1/softwareinst/instg/instg_0008.html?Mode=PmIns\&InstallType=local\&OS=openEuler\&Software=cannToolKit)
|
||||
</Accordion>
|
||||
<Accordion title="MemFabric-Hybrid">
|
||||
If you want to use PD disaggregation mode, you need to install MemFabric-Hybrid. MemFabric-Hybrid is a drop-in replacement of Mooncake Transfer Engine that enables KV cache transfer on Ascend NPU clusters.
|
||||
|
||||
```bash
|
||||
pip install memfabric-hybrid==1.0.5
|
||||
```
|
||||
</Accordion>
|
||||
<Accordion title="Pytorch and Pytorch Framework Adaptor on Ascend">
|
||||
```bash
|
||||
PYTORCH_VERSION=2.8.0
|
||||
TORCHVISION_VERSION=0.23.0
|
||||
TORCH_NPU_VERSION=2.8.0
|
||||
pip install torch==$PYTORCH_VERSION torchvision==$TORCHVISION_VERSION --index-url https://download.pytorch.org/whl/cpu
|
||||
pip install torch_npu==$TORCH_NPU_VERSION
|
||||
```
|
||||
|
||||
If you are using other versions of `torch` and install `torch_npu`, check [installation guide](https://github.com/Ascend/pytorch/blob/master/README)
|
||||
</Accordion>
|
||||
<Accordion title="Triton on Ascend">
|
||||
We provide our own implementation of Triton for Ascend.
|
||||
|
||||
```bash
|
||||
BISHENG_NAME="Ascend-BiSheng-toolkit_aarch64_20251121.run"
|
||||
BISHENG_URL="https://sglang-ascend.obs.cn-east-3.myhuaweicloud.com/sglang/triton_ascend/${BISHENG_NAME}"
|
||||
wget -O "${BISHENG_NAME}" "${BISHENG_URL}" && chmod a+x "${BISHENG_NAME}" && "./${BISHENG_NAME}" --install && rm "${BISHENG_NAME}"
|
||||
```
|
||||
|
||||
```bash
|
||||
pip install triton-ascend
|
||||
```
|
||||
|
||||
For installation of Triton on Ascend nightly builds or from sources, follow [installation guide](https://gitcode.com/Ascend/triton-ascend/blob/master/docs/sources/getting-started/installation)
|
||||
|
||||
</Accordion>
|
||||
<Accordion title="SGLang Kernels NPU">
|
||||
We provide SGL kernels for Ascend NPU, check [installation guide](https://github.com/sgl-project/sgl-kernel-npu/blob/main/python/sgl_kernel_npu/README).
|
||||
</Accordion>
|
||||
<Accordion title="DeepEP-compatible Library">
|
||||
We provide a DeepEP-compatible Library as a drop-in replacement of deepseek-ai's DeepEP library, check the [installation guide](https://github.com/sgl-project/sgl-kernel-npu/blob/main/python/deep_ep/README).
|
||||
</Accordion>
|
||||
<Accordion title="Installing SGLang from source">
|
||||
```bash
|
||||
# Use the last release branch
|
||||
git clone https://github.com/sgl-project/sglang.git
|
||||
cd sglang
|
||||
mv python/pyproject_npu.toml python/pyproject.toml
|
||||
pip install -e python[all_npu]
|
||||
```
|
||||
</Accordion>
|
||||
</AccordionGroup>
|
||||
</Tab>
|
||||
|
||||
<Tab title="Docker">
|
||||
|
||||
### Obtain Image
|
||||
|
||||
You can download the SGLang image or build an image based on Dockerfile to obtain the Ascend NPU image.
|
||||
|
||||
1. **Download SGLang image**
|
||||
|
||||
```bash
|
||||
dockerhub: docker.io/lmsysorg/sglang:$tag
|
||||
# Main-based tag, change main to specific version like v0.5.6,
|
||||
# you can get image for specific version
|
||||
Atlas 800I A3 : {main}-cann8.5.0-a3
|
||||
Atlas 800I A2: {main}-cann8.5.0-910b
|
||||
```
|
||||
|
||||
2. **Build an image based on Dockerfile**
|
||||
|
||||
```bash
|
||||
# Clone the SGLang repository
|
||||
git clone https://github.com/sgl-project/sglang.git
|
||||
cd sglang/docker
|
||||
|
||||
# Build the docker image
|
||||
# If there are network errors, please modify the Dockerfile to use offline dependencies or use a proxy
|
||||
docker build -t <image_name> -f npu.Dockerfile .
|
||||
```
|
||||
|
||||
### Create Docker
|
||||
|
||||
<Info>`--privileged` and `--network=host` are required by RDMA, which is typically needed by Ascend NPU clusters.</Info>
|
||||
<Note>The following docker command is based on Atlas 800I A3 machines. If you are using Atlas 800I A2, make sure only `davinci[0-7]` are mapped into container.</Note>
|
||||
|
||||
```bash
|
||||
alias drun='docker run -it --rm --privileged --network=host --ipc=host --shm-size=16g \
|
||||
--device=/dev/davinci0 --device=/dev/davinci1 --device=/dev/davinci2 --device=/dev/davinci3 \
|
||||
--device=/dev/davinci4 --device=/dev/davinci5 --device=/dev/davinci6 --device=/dev/davinci7 \
|
||||
--device=/dev/davinci8 --device=/dev/davinci9 --device=/dev/davinci10 --device=/dev/davinci11 \
|
||||
--device=/dev/davinci12 --device=/dev/davinci13 --device=/dev/davinci14 --device=/dev/davinci15 \
|
||||
--device=/dev/davinci_manager --device=/dev/hisi_hdc \
|
||||
--volume /usr/local/sbin:/usr/local/sbin --volume /usr/local/Ascend/driver:/usr/local/Ascend/driver \
|
||||
--volume /usr/local/Ascend/firmware:/usr/local/Ascend/firmware \
|
||||
--volume /etc/ascend_install.info:/etc/ascend_install.info \
|
||||
--volume /var/queue_schedule:/var/queue_schedule --volume ~/.cache/:/root/.cache/'
|
||||
|
||||
# Add HF_TOKEN env for download model by SGLang.
|
||||
drun --env "HF_TOKEN=<secret>" \
|
||||
<image_name> \
|
||||
python3 -m sglang.launch_server --model-path meta-llama/Llama-3.1-8B-Instruct --attention-backend ascend
|
||||
```
|
||||
|
||||
</Tab>
|
||||
</Tabs>
|
||||
|
||||
## System Settings
|
||||
|
||||
<AccordionGroup>
|
||||
<Accordion title="CPU performance power scheme" defaultOpen="true">
|
||||
The default power scheme on Ascend hardware is `ondemand` which could affect performance, changing it to `performance` is recommended.
|
||||
|
||||
```bash
|
||||
echo performance | sudo tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
|
||||
|
||||
# Make sure changes are applied successfully
|
||||
cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_governor # shows performance
|
||||
```
|
||||
</Accordion>
|
||||
<Accordion title="Disable NUMA balancing" defaultOpen="true">
|
||||
```bash
|
||||
sudo sysctl -w kernel.numa_balancing=0
|
||||
# Check
|
||||
cat /proc/sys/kernel/numa_balancing # shows 0
|
||||
```
|
||||
</Accordion>
|
||||
<Accordion title="Prevent swapping out system memory" defaultOpen="true">
|
||||
```bash
|
||||
sudo sysctl -w vm.swappiness=10
|
||||
|
||||
# Check
|
||||
cat /proc/sys/vm/swappiness # shows 10
|
||||
```
|
||||
</Accordion>
|
||||
</AccordionGroup>
|
||||
|
||||
## Running SGLang Service
|
||||
|
||||
<Tabs>
|
||||
<Tab title="For Large Language Models">
|
||||
|
||||
### PD Mixed Scene
|
||||
|
||||
```bash
|
||||
# Enabling CPU Affinity
|
||||
export SGLANG_SET_CPU_AFFINITY=1
|
||||
python3 -m sglang.launch_server --model-path meta-llama/Llama-3.1-8B-Instruct --attention-backend ascend
|
||||
```
|
||||
|
||||
### PD Separation Scene
|
||||
|
||||
1. **Launch Prefill Server**
|
||||
|
||||
```bash
|
||||
# Enabling CPU Affinity
|
||||
export SGLANG_SET_CPU_AFFINITY=1
|
||||
|
||||
# PIP: recommended to config first Prefill Server IP
|
||||
# PORT: one free port
|
||||
# all sglang servers need to be config the same PIP and PORT,
|
||||
export ASCEND_MF_STORE_URL="tcp://PIP:PORT"
|
||||
# if you are Atlas 800I A2 hardware and use rdma for kv cache transfer, add this parameter
|
||||
export ASCEND_MF_TRANSFER_PROTOCOL="device_rdma"
|
||||
python3 -m sglang.launch_server \
|
||||
--model-path meta-llama/Llama-3.1-8B-Instruct \
|
||||
--disaggregation-mode prefill \
|
||||
--disaggregation-transfer-backend ascend \
|
||||
--disaggregation-bootstrap-port 8995 \
|
||||
--attention-backend ascend \
|
||||
--device npu \
|
||||
--base-gpu-id 0 \
|
||||
--tp-size 1 \
|
||||
--host 127.0.0.1 \
|
||||
--port 8000
|
||||
```
|
||||
|
||||
2. **Launch Decode Server**
|
||||
|
||||
```bash
|
||||
# PIP: recommended to config first Prefill Server IP
|
||||
# PORT: one free port
|
||||
# all sglang servers need to be config the same PIP and PORT,
|
||||
export ASCEND_MF_STORE_URL="tcp://PIP:PORT"
|
||||
# if you are Atlas 800I A2 hardware and use rdma for kv cache transfer, add this parameter
|
||||
export ASCEND_MF_TRANSFER_PROTOCOL="device_rdma"
|
||||
python3 -m sglang.launch_server \
|
||||
--model-path meta-llama/Llama-3.1-8B-Instruct \
|
||||
--disaggregation-mode decode \
|
||||
--disaggregation-transfer-backend ascend \
|
||||
--attention-backend ascend \
|
||||
--device npu \
|
||||
--base-gpu-id 1 \
|
||||
--tp-size 1 \
|
||||
--host 127.0.0.1 \
|
||||
--port 8001
|
||||
```
|
||||
|
||||
3. **Launch Router**
|
||||
|
||||
```bash
|
||||
python3 -m sglang_router.launch_router \
|
||||
--pd-disaggregation \
|
||||
--policy cache_aware \
|
||||
--prefill http://127.0.0.1:8000 8995 \
|
||||
--decode http://127.0.0.1:8001 \
|
||||
--host 127.0.0.1 \
|
||||
--port 6688
|
||||
```
|
||||
</Tab>
|
||||
<Tab title="For Multimodal Language Models">
|
||||
|
||||
### PD Mixed Scene
|
||||
|
||||
```bash
|
||||
python3 -m sglang.launch_server \
|
||||
--model-path Qwen3-VL-30B-A3B-Instruct \
|
||||
--host 127.0.0.1 \
|
||||
--port 8000 \
|
||||
--tp 4 \
|
||||
--device npu \
|
||||
--attention-backend ascend \
|
||||
--mm-attention-backend ascend_attn \
|
||||
--disable-radix-cache \
|
||||
--trust-remote-code \
|
||||
--enable-multimodal \
|
||||
--sampling-backend ascend
|
||||
```
|
||||
|
||||
</Tab>
|
||||
</Tabs>
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,610 @@
|
||||
This section describes the models supported on the Ascend NPU, including Large Language Models, Multimodal Language
|
||||
Models, Embedding Models, Reward Models and Rerank Models. Mainstream DeepSeek/Qwen/GLM series are included.
|
||||
You are welcome to enable various models based on your business requirements.
|
||||
|
||||
<Accordion title="Large Language Models">
|
||||
|
||||
|
||||
<table style={{width: "100%", borderCollapse: "collapse", tableLayout: "fixed"}}>
|
||||
<colgroup>
|
||||
<col style={{width: "25.0%"}} />
|
||||
<col style={{width: "25.0%"}} />
|
||||
<col style={{width: "25.0%"}} />
|
||||
<col style={{width: "25.0%"}} />
|
||||
</colgroup>
|
||||
<thead>
|
||||
<tr style={{borderBottom: "2px solid #d55816"}}>
|
||||
<th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.02)"}}>Models</th>
|
||||
<th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.05)"}}>Model Family</th>
|
||||
<th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.02)"}}>A2</th>
|
||||
<th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.05)"}}>A3</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>DeepSeek V3/V3.1</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>DeepSeek</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>vllm-ascend/DeepSeek-V3.2-Exp-W8A8</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>DeepSeek</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>vllm-ascend/DeepSeek-R1-0528-W8A8</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>DeepSeek</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>vllm-ascend/DeepSeek-V2-Lite-W8A8</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>DeepSeek</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Qwen/Qwen3-30B-A3B-Instruct-2507</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Qwen</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Qwen/Qwen3-32B</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Qwen</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Qwen/Qwen3-0.6B</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Qwen</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>vllm-ascend/Qwen3-235B-A22B-W8A8</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Qwen</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Qwen/Qwen3-Next-80B-A3B-Instruct</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Qwen</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Qwen3-Coder-480B-A35B-Instruct-w8a8-QuaRot</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Qwen</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Qwen/Qwen2.5-7B-Instruct</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Qwen</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>vllm-ascend/QWQ-32B-W8A8</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Qwen</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>meta-llama/Llama-4-Scout-17B-16E-Instruct</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Llama</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>AI-ModelScope/Llama-3.1-8B-Instruct</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Llama</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>LLM-Research/llama-2-7b</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Llama</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>LLM-Research/Llama-3.2-1B-Instruct</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Llama</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>mistralai/Mistral-7B-Instruct-v0.2</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Mistral</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>google/gemma-3-4b-it</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Gemma</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>microsoft/Phi-4-multimodal-instruct</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Phi</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>allenai/OLMoE-1B-7B-0924</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>OLMoE</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>stabilityai/stablelm-2-1_6b</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>StableLM</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>CohereForAI/c4ai-command-r-v01</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Command-R</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>huihui-ai/grok-2</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Grok</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>ZhipuAI/chatglm2-6b</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>ChatGLM</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Shanghai_AI_Laboratory/internlm2-7b</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>InternLM 2</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>ExaONE 3</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>xverse/XVERSE-MoE-A36B</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>XVERSE</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>HuggingFaceTB/SmolLM-1.7B</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>SmolLM</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>ZhipuAI/glm-4-9b-chat</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>GLM-4</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>XiaomiMiMo/MiMo-7B-RL</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>MiMo</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>arcee-ai/AFM-4.5B-Base</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Arcee AFM-4.5B</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Howeee/persimmon-8b-chat</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Persimmon</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>inclusionAI/Ling-lite</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Ling</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>ibm-granite/granite-3.1-8b-instruct</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Granite</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>ibm-granite/granite-3.0-3b-a800m-instruct</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Granite MoE</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>AI-ModelScope/dbrx-instruct</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>DBRX (Databricks)</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>baichuan-inc/Baichuan2-13B-Chat</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Baichuan 2 (7B, 13B)</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>baidu/ERNIE-4.5-21B-A3B-PT</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>ERNIE-4.5 (4.5, 4.5MoE series)</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>OpenBMB/MiniCPM3-4B</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>MiniCPM (v3, 4B)</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Kimi/Kimi-K2-Thinking</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Kimi</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>openai/gpt-oss-120b</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>GPTOSS</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>allenai/OLMo-2-1124-7B-Instruct</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>OLMo</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>minimax/MiniMax-M2</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>MiniMax-M2</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>upstage/SOLAR-10.7B-Instruct-v1.0</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Solar</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>bigcode/starcoder2-7b</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>StarCoder2</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>arcee-ai/Trinity-Mini</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Trinity (Nano, Mini)</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
|
||||
</Accordion>
|
||||
|
||||
|
||||
<Accordion title="Multimodal Language Models">
|
||||
|
||||
|
||||
<table style={{width: "100%", borderCollapse: "collapse", tableLayout: "fixed"}}>
|
||||
<colgroup>
|
||||
<col style={{width: "25.0%"}} />
|
||||
<col style={{width: "25.0%"}} />
|
||||
<col style={{width: "25.0%"}} />
|
||||
<col style={{width: "25.0%"}} />
|
||||
</colgroup>
|
||||
<thead>
|
||||
<tr style={{borderBottom: "2px solid #d55816"}}>
|
||||
<th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.02)"}}>Models</th>
|
||||
<th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.05)"}}>Model Family (Variants)</th>
|
||||
<th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.02)"}}>A2</th>
|
||||
<th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.05)"}}>A3</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Qwen/Qwen2.5-VL-3B-Instruct</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Qwen-VL</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Qwen/Qwen2.5-VL-72B-Instruct</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Qwen-VL</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Qwen/Qwen3-VL-30B-A3B-Instruct</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Qwen-VL</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Qwen/Qwen3-VL-8B-Instruct</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Qwen-VL</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Qwen/Qwen3-VL-4B-Instruct</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Qwen-VL</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Qwen/Qwen3-VL-235B-A22B-Instruct</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Qwen-VL</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>deepseek-ai/deepseek-vl2</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>DeepSeek-VL2</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>deepseek-ai/Janus-Pro-1B</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Janus-Pro (1B, 7B)</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>deepseek-ai/Janus-Pro-7B</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Janus-Pro (1B, 7B)</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>openbmb/MiniCPM-V-2_6</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>MiniCPM-V / MiniCPM-o</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>openbmb/MiniCPM-o-2_6</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>MiniCPM-V / MiniCPM-o</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>google/gemma-3-4b-it</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Gemma 3 (Multimodal)</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>mistralai/Mistral-Small-3.1-24B-Instruct-2503</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Mistral-Small-3.1-24B</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>microsoft/Phi-4-multimodal-instruct</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Phi-4-multimodal-instruct</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>XiaomiMiMo/MiMo-VL-7B-RL</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>MiMo-VL (7B)</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>AI-ModelScope/llava-v1.6-34b</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>LLaVA (v1.5 & v1.6)</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>lmms-lab/llava-next-72b</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>LLaVA-NeXT (8B, 72B)</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>lmms-lab/llava-onevision-qwen2-7b-ov</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>LLaVA-OneVision</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Kimi/Kimi-VL-A3B-Instruct</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Kimi-VL (A3B)</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>ZhipuAI/GLM-4.5V</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>GLM-4.5V (106B)</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>LLM-Research/Llama-3.2-11B-Vision-Instruct</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Llama 3.2 Vision (11B)</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>rednote-hilab/dots.ocr</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>DotsVLM-OCR</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
|
||||
</Accordion>
|
||||
|
||||
|
||||
<Accordion title="Embedding Models">
|
||||
|
||||
|
||||
<table style={{width: "100%", borderCollapse: "collapse", tableLayout: "fixed"}}>
|
||||
<colgroup>
|
||||
<col style={{width: "25.0%"}} />
|
||||
<col style={{width: "25.0%"}} />
|
||||
<col style={{width: "25.0%"}} />
|
||||
<col style={{width: "25.0%"}} />
|
||||
</colgroup>
|
||||
<thead>
|
||||
<tr style={{borderBottom: "2px solid #d55816"}}>
|
||||
<th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.02)"}}>Models</th>
|
||||
<th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.05)"}}>Model Family</th>
|
||||
<th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.02)"}}>A2</th>
|
||||
<th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.05)"}}>A3</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>intfloat/e5-mistral-7b-instruct</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>E5 (Llama/Mistral based)</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>iic/gte_Qwen2-1.5B-instruct</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>GTE-Qwen2</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Qwen/Qwen3-Embedding-8B</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Qwen3-Embedding</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Alibaba-NLP/gme-Qwen2-VL-2B-Instruct</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>GME (Multimodal)</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>AI-ModelScope/clip-vit-large-patch14-336</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>CLIP</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>BAAI/bge-large-en-v1.5</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>BGE</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
|
||||
</Accordion>
|
||||
|
||||
|
||||
<Accordion title="Reward Models">
|
||||
|
||||
|
||||
<table style={{width: "100%", borderCollapse: "collapse", tableLayout: "fixed"}}>
|
||||
<colgroup>
|
||||
<col style={{width: "25.0%"}} />
|
||||
<col style={{width: "25.0%"}} />
|
||||
<col style={{width: "25.0%"}} />
|
||||
<col style={{width: "25.0%"}} />
|
||||
</colgroup>
|
||||
<thead>
|
||||
<tr style={{borderBottom: "2px solid #d55816"}}>
|
||||
<th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.02)"}}>Models</th>
|
||||
<th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.05)"}}>Model Family</th>
|
||||
<th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.02)"}}>A2</th>
|
||||
<th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.05)"}}>A3</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Skywork/Skywork-Reward-Llama-3.1-8B-v0.2</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Llama3.1 Reward</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Shanghai_AI_Laboratory/internlm2-7b-reward</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>InternLM 2 Reward</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Qwen/Qwen2.5-Math-RM-72B</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Qwen2.5 Reward - Math</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Howeee/Qwen2.5-1.5B-apeach</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Qwen2.5 Reward - Sequence</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>AI-ModelScope/Skywork-Reward-Gemma-2-27B-v0.2</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Gemma 2-27B Reward</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
|
||||
</Accordion>
|
||||
|
||||
|
||||
<Accordion title="Rerank Models">
|
||||
|
||||
|
||||
<table style={{width: "100%", borderCollapse: "collapse", tableLayout: "fixed"}}>
|
||||
<colgroup>
|
||||
<col style={{width: "25.0%"}} />
|
||||
<col style={{width: "25.0%"}} />
|
||||
<col style={{width: "25.0%"}} />
|
||||
<col style={{width: "25.0%"}} />
|
||||
</colgroup>
|
||||
<thead>
|
||||
<tr style={{borderBottom: "2px solid #d55816"}}>
|
||||
<th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.02)"}}>Models</th>
|
||||
<th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.05)"}}>Model Family</th>
|
||||
<th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.02)"}}>A2</th>
|
||||
<th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.05)"}}>A3</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>BAAI/bge-reranker-v2-m3</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>BGE-Reranker</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>✅</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>✅</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
</Accordion>
|
||||
Reference in New Issue
Block a user