minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 10 Packages Projects Releases Wiki Activity

Update ascend docs (#20846)

Browse Source
This commit is contained in:
amote-i
2026-03-25 09:58:44 +03:00
committed by GitHub
parent 5297a3cb46
commit 2d583799eb
5 changed files with 24 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/platforms/ascend_npu_best_practice.md
+9 -10
View File
@@ -148,7 +148,7 @@ do
--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 \
--tokenizer-worker-num 4 --disable-shared-experts-fusion --dtype bfloat16 \
--load-balance-method decode_round_robin
NODE_RANK=$i
break
@@ -265,7 +265,7 @@ do
--moe-a2a-backend deepep --enable-dp-attention --deepep-mode low_latency --enable-dp-lm-head --moe-dense-tp 1 \
--cuda-graph-bs 2 4 6 --disaggregation-transfer-backend ascend --watchdog-timeout 9000 --context-length 8192 \
--speculative-algorithm NEXTN --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4 \
--tokenizer-worker-num 4 --prefill-round-robin-balance --disable-shared-experts-fusion --dtype bfloat16 \
--tokenizer-worker-num 4 --disable-shared-experts-fusion --dtype bfloat16 \
--load-balance-method decode_round_robin
NODE_RANK=$i
break
@@ -549,8 +549,8 @@ do
--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 24 --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 \
--prefill-round-robin-balance --disable-shared-experts-fusion --dtype bfloat16 --tokenizer-worker-num 4 \
--load-balance-method decode_round_robin
--disable-shared-experts-fusion --dtype bfloat16 --tokenizer-worker-num 4 \
--load-balance-method decode_round_robin
NODE_RANK=$i
break
fi
@@ -750,8 +750,8 @@ do
--moe-a2a-backend deepep --enable-dp-attention --deepep-mode low_latency --enable-dp-lm-head \
--cuda-graph-bs 8 10 12 14 16 18 20 22 24 --disaggregation-transfer-backend ascend --watchdog-timeout 9000 --context-length 8192 \
--speculative-algorithm NEXTN --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4 \
--prefill-round-robin-balance --disable-shared-experts-fusion --dtype bfloat16 --tokenizer-worker-num 4 \
--load-balance-method decode_round_robin
--disable-shared-experts-fusion --dtype bfloat16 --tokenizer-worker-num 4 \
--load-balance-method decode_round_robin
NODE_RANK=$i
break
fi
@@ -964,7 +964,6 @@ python3 -m sglang.launch_server --model-path ${MODEL_PATH} \
--speculative-algorithm NEXTN --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4 \
--disaggregation-transfer-backend ascend \
--disaggregation-mode decode \
--prefill-round-robin-balance \
--load-balance-method round_robin \
--nnodes $nnodes --node-rank $VC_TASK_INDEX \
--dist-init-addr ${IPs[0]}:10000 --load-balance-method decode_round_robin
@@ -1097,7 +1096,7 @@ do
--speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4 \
--dist-init-addr xxx:5000 \
--disaggregation-transfer-backend ascend --watchdog-timeout 9000 --context-length 8192 \
--prefill-round-robin-balance --enable-dp-lm-head --dtype bfloat16 --tokenizer-worker-num 4 \
--enable-dp-lm-head --dtype bfloat16 --tokenizer-worker-num 4 \
--load-balance-method decode_round_robin
NODE_RANK=$i
break
@@ -2016,8 +2015,8 @@ do
--attention-backend ascend --device npu --quantization modelslim --enable-dp-attention \
--moe-a2a-backend ascend_fuseep --cuda-graph-bs 16 32 48 56 64 72 80 88 96 \
--dist-init-addr DIP1:5000 \
--disaggregation-transfer-backend ascend --watchdog-timeout 9000 --context-length 8192 \
--prefill-round-robin-balance --enable-dp-lm-head --dtype bfloat16 --tokenizer-worker-num 4 --load-balance-method decode_round_robin
--disaggregation-transfer-backend ascend --watchdog-timeout 9000 --context-length 8192 \
--enable-dp-lm-head --dtype bfloat16 --tokenizer-worker-num 4 --load-balance-method decode_round_robin
NODE_RANK=$i
break
fi
docs/platforms/ascend_npu_deepseek_example.md
+1 -2
View File
@@ -143,7 +143,6 @@ python -m sglang.launch_server \
--attention-backend ascend \
--device npu \
--quantization modelslim \
--prefill-round-robin-balance \
--moe-a2a-backend deepep \
--enable-dp-attention \
--deepep-mode low_latency \
@@ -252,7 +251,7 @@ do
--moe-a2a-backend deepep --enable-dp-attention --deepep-mode low_latency --enable-dp-lm-head --moe-dense-tp 1 \
--cuda-graph-bs 12 14 16 18 20 22 24 26 --disaggregation-transfer-backend ascend --watchdog-timeout 9000 --context-length 8192 \
--speculative-algorithm NEXTN --speculative-num-steps 2 --speculative-eagle-topk 1 --speculative-num-draft-tokens 3 \
--tokenizer-worker-num 4 --prefill-round-robin-balance --disable-shared-experts-fusion --dtype bfloat16 \
--tokenizer-worker-num 4 --disable-shared-experts-fusion --dtype bfloat16 \
--load-balance-method decode_round_robin
NODE_RANK=$i
break
docs/platforms/ascend_npu_glm5_examples.md
+1 -1
View File
@@ -15,7 +15,7 @@ The GLM (General Language Model) series is an open-source bilingual large langua
### Installation
The dependencies required for the NPU runtime environment have been integrated into a Docker image and uploaded to the Ascend platform. You can directly pull it.
The dependencies required for the NPU runtime environment have been integrated into a Docker image and uploaded to the online platform. You can directly pull it.
```{code-block} bash
#Atlas 800 A3
docs/platforms/ascend_npu_support_features.md
+11 -3
View File
@@ -72,6 +72,11 @@ click [Server Arguments](https://docs.sglang.io/advanced_features/server_argumen
| `--swa-full-tokens-ratio` | `0.8` | Type: float | A2, A3 |
| `--disable-hybrid-swa-memory` | `False` | bool flag<br/> (set to enable) | A2, A3 |
| `--radix-eviction-policy` | `lru` | `lru`,<br/>`lfu` | A2, A3 |
| `--enable-prefill-delayer` | `False` | bool flag<br/> (set to enable) | A2, A3 |
| `--prefill-delayer-max-delay-passes` | `30` | Type: int | A2, A3 |
| `--prefill-delayer-token-usage-low-watermark` | `None` | Type: float | A2, A3 |
| `--prefill-delayer-forward-passes-buckets` | `None` | List[float] | A2, A3 |
| `--prefill-delayer-wait-seconds-buckets` | `None` | List[float] | A2, A3 |
| `--abort-on-priority-`<br/>`when-disabled` | `False` | bool flag<br/> (set to enable) | A2, A3 |
| `--enable-dynamic-chunking` | `False` | bool flag<br/> (set to enable) | A2, A3 |
@@ -82,6 +87,8 @@ click [Server Arguments](https://docs.sglang.io/advanced_features/server_argumen
| `--device` | `None` | Type: str | A2, A3 |
| `--tensor-parallel-size`<br/>`--tp-size` | `1` | Type: int | A2, A3 |
| `--pipeline-parallel-size`<br/>`--pp-size` | `1` | Type: int | A2, A3 |
| `--attention-context-parallel-size`<br/>`--attn-cp-size` | `1` | Type: int | A2, A3 |
| `--moe-data-parallel-size`<br/>`--moe-dp-size` | `1` | Type: int | A2, A3 |
| `--pp-max-micro-batch-size` | `None` | Type: int | A2, A3 |
| `--pp-async-batch-depth` | `None` | Type: int | A2, A3 |
| `--stream-interval` | `1` | Type: int | A2, A3 |
@@ -92,6 +99,8 @@ click [Server Arguments](https://docs.sglang.io/advanced_features/server_argumen
| `--watchdog-timeout` | `300` | Type: float | A2, A3 |
| `--soft-watchdog-timeout` | `300` | Type: float | A2, A3 |
| `--dist-timeout` | `None` | Type: int | A2, A3 |
| `--download-dir` | `None` | Type: str | A2, A3 |
| `--model-checksum` | `None` | Type: str | A2, A3 |
| `--base-gpu-id` | `0` | Type: int | A2, A3 |
| `--gpu-id-step` | `1` | Type: int | A2, A3 |
| `--sleep-on-idle` | `False` | bool flag (set to enable) | A2, A3 |
@@ -142,6 +151,7 @@ click [Server Arguments](https://docs.sglang.io/advanced_features/server_argumen
| `--served-model-name` | `None` | Type: str | A2, A3 |
| `--weight-version` | `default` | Type: str | A2, A3 |
| `--chat-template` | `None` | Type: str | A2, A3 |
| `--hf-chat-template-name` | `None` | Type: str | A2, A3 |
| `--completion-template` | `None` | Type: str | A2, A3 |
| `--enable-cache-report` | `False` | bool flag<br/> (set to enable) | A2, A3 |
| `--reasoning-parser` | `None` | `deepseek-r1`<br/>`deepseek-v3`<br/>`glm45`<br/>`gpt-oss`<br/>`kimi`<br/>`qwen3`<br/>`qwen3-thinking`<br/>`step3` | A2, A3 |
@@ -154,7 +164,6 @@ click [Server Arguments](https://docs.sglang.io/advanced_features/server_argumen
|----------------------------------------|---------------|-----------------------------------------------------------|:----------------:|
| `--data-parallel-size`<br/>`--dp-size` | `1` | Type: int | A2, A3 |
| `--load-balance-method` | `auto` | `auto`,<br/> `round_robin`,<br/> `follow_bootstrap_room`,<br/> `total_requests`,<br/> `total_tokens` | A2, A3 |
| `--prefill-round-robin-balance` | `False` | bool flag<br/> (set to enable) | A2, A3 |
## Multi-node distributed serving
@@ -389,7 +398,6 @@ click [Server Arguments](https://docs.sglang.io/advanced_features/server_argumen
| `--disaggregation-bootstrap-port` | `8998` | Type: int | A2, A3 |
| `--disaggregation-ib-device` | `None` | Type: str | Special for GPU |
| `--disaggregation-decode-`<br/>`enable-offload-kvcache` | `False` | bool flag<br/> (set to enable) | A2, A3 |
| `--disaggregation-decode-`<br/>`enable-fake-auto` | `False` | bool flag<br/> (set to enable) | A2, A3 |
| `--num-reserved-decode-tokens` | `512` | Type: int | A2, A3 |
| `--disaggregation-decode-`<br/>`polling-interval` | `1` | Type: int | A2, A3 |
@@ -464,7 +472,7 @@ NPU, like Ktransformer, checkpoint-engine etc.
| `--kt-weight-path` | `None` | Type: str |
| `--kt-method` | `AMXINT4` | Type: str |
| `--kt-cpuinfer` | `None` | Type: int |
| `--kt-threadpool-count` | 2 | Type: int |
| `--kt-threadpool-count` | `2` | Type: int |
| `--kt-num-gpu-experts` | `None` | Type: int |
| `--kt-max-deferred-`<br/>`experts-per-token` | `None` | Type: int |
docs/platforms/ascend_npu_support_models.md
+2 -2
View File
@@ -48,9 +48,9 @@ You are welcome to enable various models based on your business requirements.
| baidu/ERNIE-4.5-21B-A3B-PT | ERNIE-4.5 (4.5, 4.5MoE series) | **<span style="color: green;">√</span>** | **<span style="color: green;">√</span>** |
| OpenBMB/MiniCPM3-4B | MiniCPM (v3, 4B) | **<span style="color: green;">√</span>** | **<span style="color: green;">√</span>** |
| Kimi/Kimi-K2-Thinking | Kimi | **<span style="color: green;">√</span>** | **<span style="color: green;">√</span>** |
| openai/gpt-oss-120b | GPTOSS | **<span style="color: green;">√</span>** | **<span style="color: green;">√</span>** |
| eigen-ai-labs/gpt-oss-120b-bf16 | GPTOSS | **<span style="color: green;">√</span>** | **<span style="color: green;">√</span>** |
| allenai/OLMo-2-1124-7B-Instruct | OLMo | **<span style="color: green;">√</span>** | **<span style="color: green;">√</span>** |
| minimax/MiniMax-M2 | MiniMax-M2 | **<span style="color: green;">√</span>** | **<span style="color: green;">√</span>** |
| cyankiwi/MiniMax-M2-BF16 | MiniMax-M2 | **<span style="color: green;">√</span>** | **<span style="color: green;">√</span>** |
| upstage/SOLAR-10.7B-Instruct-v1.0 | Solar | **<span style="color: green;">√</span>** | **<span style="color: green;">√</span>** |
| bigcode/starcoder2-7b | StarCoder2 | **<span style="color: green;">√</span>** | **<span style="color: green;">√</span>** |
| arcee-ai/Trinity-Mini | Trinity (Nano, Mini) | **<span style="color: green;">√</span>** | **<span style="color: green;">√</span>** |