diff --git a/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_support_features.mdx b/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_support_features.mdx
index 408f62f21..63efb4f1c 100644
--- a/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_support_features.mdx
+++ b/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_support_features.mdx
@@ -43,7 +43,7 @@ click [Server Arguments](../../advanced_features/server_arguments).
| `--tokenizer-mode` |
`auto` |
- auto, slow |
+ `auto`, `slow` |
A2, A3 |
@@ -61,7 +61,7 @@ click [Server Arguments](../../advanced_features/server_arguments).
| `--load-format` |
`auto` |
- auto, safetensors, gguf |
+ `auto`, `safetensors`, `gguf` |
A2, A3 |
@@ -103,7 +103,7 @@ click [Server Arguments](../../advanced_features/server_arguments).
| `--model-impl` |
`auto` |
- auto, sglang, transformers |
+ `auto`, `sglang`, `transformers` |
A2, A3 |
@@ -167,7 +167,7 @@ click [Server Arguments](../../advanced_features/server_arguments).
| `--grpc-mode` |
`False` |
- False |
+ `False` |
Planned |
@@ -248,7 +248,7 @@ click [Server Arguments](../../advanced_features/server_arguments).
| `--dtype` |
`auto` |
- auto, float16, bfloat16 |
+ `auto`, `float16`, `bfloat16` |
A2, A3 |
@@ -378,7 +378,7 @@ click [Server Arguments](../../advanced_features/server_arguments).
| `--schedule-policy` |
`fcfs` |
- lpm, fcfs |
+ `lpm`, `fcfs` |
A2, A3 |
@@ -436,43 +436,43 @@ click [Server Arguments](../../advanced_features/server_arguments).
| Planned |
- --radix-eviction-policy |
- lru |
- lru,
lfu |
+ `--radix-eviction-policy` |
+ `lru` |
+ `lru`, `lfu` |
A2, A3 |
- --enable-prefill-delayer |
+ `--enable-prefill-delayer` |
`False` |
bool flag (set to enable) |
A2, A3 |
- --prefill-delayer-max-delay-passes |
- 30 |
+ `--prefill-delayer-max-delay-passes` |
+ `30` |
Type: int |
A2, A3 |
- --prefill-delayer-token-usage-low-watermark |
- None |
+ `--prefill-delayer-token-usage-low-watermark` |
+ `None` |
Type: float |
A2, A3 |
- --prefill-delayer-forward-passes-buckets |
- None |
+ `--prefill-delayer-forward-passes-buckets` |
+ `None` |
List[float] |
A2, A3 |
- --prefill-delayer-wait-seconds-buckets |
- None |
+ `--prefill-delayer-wait-seconds-buckets` |
+ `None` |
List[float] |
A2, A3 |
- --abort-on-priority-
when-disabled |
+ `--abort-on-priority-` `when-disabled` |
`False` |
bool flag (set to enable) |
A2, A3 |
@@ -520,132 +520,132 @@ click [Server Arguments](../../advanced_features/server_arguments).
`--pipeline-parallel-size` `--pp-size` |
`1` |
- Type: int; Currently 2 not supported |
+ Type: int; Currently `2` not supported |
Experimental |
- --attention-context-parallel-size
--attn-cp-size |
- 1 |
+ `--attention-context-parallel-size` `--attn-cp-size` |
+ `1` |
Type: int; must be equal to --tp-size |
A2, A3 |
- --moe-data-parallel-size
--moe-dp-size |
- 1 |
+ `--moe-data-parallel-size` `--moe-dp-size` |
+ `1` |
Type: int |
Planned |
- --pp-max-micro-batch-size |
- None |
+ `--pp-max-micro-batch-size` |
+ `None` |
Type: int |
Experimental |
- --pp-async-batch-depth |
- None |
+ `--pp-async-batch-depth` |
+ `None` |
Type: int |
Experimental |
- --stream-interval |
- 1 |
+ `--stream-interval` |
+ `1` |
Type: int |
A2, A3 |
- --incremental-streaming-output |
- False |
+ `--incremental-streaming-output` |
+ `False` |
bool flag (set to enable) |
A2, A3 |
- --stream-response-default-include-usage |
- False |
+ `--stream-response-default-include-usage` |
+ `False` |
bool flag (set to enable) |
A2, A3 |
- --enable-streaming-session |
- False |
+ `--enable-streaming-session` |
+ `False` |
bool flag (set to enable) |
A2, A3 |
- --random-seed |
- None |
+ `--random-seed` |
+ `None` |
Type: int |
A2, A3 |
- --constrained-json-
whitespace-pattern |
- None |
+ `--constrained-json-` `whitespace-pattern` |
+ `None` |
Type: str |
A2, A3 |
- --constrained-json-
disable-any-whitespace |
- False |
+ `--constrained-json-` `disable-any-whitespace` |
+ `False` |
bool flag (set to enable) |
A2, A3 |
- --watchdog-timeout |
- 300 |
+ `--watchdog-timeout` |
+ `300` |
Type: float |
A2, A3 |
- --soft-watchdog-timeout |
- 300 |
+ `--soft-watchdog-timeout` |
+ `300` |
Type: float |
A2, A3 |
- --dist-timeout |
- None |
+ `--dist-timeout` |
+ `None` |
Type: int |
A2, A3 |
- --download-dir |
- None |
+ `--download-dir` |
+ `None` |
Type: str |
A2, A3 |
- --model-checksum |
+ `--model-checksum` |
`None` |
Type: str |
Planned |
- --base-gpu-id |
- 0 |
+ `--base-gpu-id` |
+ `0` |
Type: int |
A2, A3 |
- --gpu-id-step |
- 1 |
+ `--gpu-id-step` |
+ `1` |
Type: int |
A2, A3 |
- --sleep-on-idle |
- False |
+ `--sleep-on-idle` |
+ `False` |
bool flag (set to enable) |
A2, A3 |
- --use-ray |
- False |
+ `--use-ray` |
+ `False` |
bool flag (set to enable) |
A2, A3 |
- --custom-sigquit-handler |
- None |
+ `--custom-sigquit-handler` |
+ `None` |
Only for engine |
A2, A3 |
@@ -693,13 +693,13 @@ click [Server Arguments](../../advanced_features/server_arguments).
| `--log-requests-level` |
`2` |
- 0, 1, 2, 3 |
+ `0`, `1`, `2`, `3` |
A2, A3 |
| `--log-requests-format` |
text |
- text, json |
+ `text`, `json` |
A2, A3 |
@@ -817,14 +817,14 @@ click [Server Arguments](../../advanced_features/server_arguments).
| A2, A3 |
- --log-requests-target |
- None |
+ `--log-requests-target` |
+ `None` |
Type: str |
A2, A3 |
- --uvicorn-access-log-exclude-prefixes |
- [] |
+ `--uvicorn-access-log-exclude-prefixes` |
+ `[]` |
List[str] |
A2, A3 |
@@ -915,45 +915,45 @@ click [Server Arguments](../../advanced_features/server_arguments).
A2, A3 |
- --hf-chat-template-name |
+ `--hf-chat-template-name` |
`None` |
Type: str |
A2, A3 |
- --completion-template |
- None |
+ `--completion-template` |
+ `None` |
Type: str |
A2, A3 |
- --file-storage-path |
- sglang_storage |
+ `--file-storage-path` |
+ `sglang_storage` |
Type: str |
Unused reserved parameter |
- --enable-cache-report |
- False |
+ `--enable-cache-report` |
+ `False` |
bool flag (set to enable) |
A2, A3 |
- --reasoning-parser |
+ `--reasoning-parser` |
`None` |
- deepseek-r1
deepseek-v3
glm45
gpt-oss
kimi
qwen3
qwen3-thinking
step3 |
+ `deepseek-r1` `deepseek-v3` `glm45` `gpt-oss` `kimi` `qwen3` `qwen3-thinking` `step3` |
A2, A3 |
- --tool-call-parser |
- None |
- llama3 pythonic qwen qwen3_coder |
+ `--tool-call-parser` |
+ `None` |
+ `llama3` `pythonic` `qwen` `qwen3_coder` |
A2, A3 |
| `--sampling-defaults` |
`model` |
- openai, model |
+ `openai`, `model` |
A2, A3 |
@@ -986,8 +986,8 @@ click [Server Arguments](../../advanced_features/server_arguments).
| `--load-balance-method` |
- auto |
- auto, round_robin, follow_bootstrap_room, total_requests, total_tokens |
+ `auto` |
+ `auto`, `round_robin`, `follow_bootstrap_room`, `total_requests`, `total_tokens` |
A2, A3 |
@@ -1094,75 +1094,75 @@ click [Server Arguments](../../advanced_features/server_arguments).
A2, A3 |
- --enable-lora-overlap-loading |
- False |
+ `--enable-lora-overlap-loading` |
+ `False` |
Bool flag (set to enable) |
A2, A3 |
- --max-lora-rank |
+ `--max-lora-rank` |
`None` |
Type: int |
A2, A3 |
- --lora-target-modules |
+ `--lora-target-modules` |
`None` |
- all |
+ `all` |
A2, A3 |
- --lora-paths |
- None |
+ `--lora-paths` |
+ `None` |
Type: List[str] / JSON objects |
A2, A3 |
- --max-loras-per-batch |
- 8 |
+ `--max-loras-per-batch` |
+ `8` |
Type: int |
A2, A3 |
- --max-loaded-loras |
- None |
+ `--max-loaded-loras` |
+ `None` |
Type: int |
A2, A3 |
- --lora-eviction-policy |
- lru |
- lru, fifo |
+ `--lora-eviction-policy` |
+ `lru` |
+ `lru`, `fifo` |
A2, A3 |
- --lora-backend |
- csgmv |
- triton,
csgmv,
ascend,
torch_native |
+ `--lora-backend` |
+ `csgmv` |
+ `triton`, `csgmv`, `ascend`, `torch_native` |
A2, A3 |
- --experts-shared-outer-loras |
- None |
+ `--experts-shared-outer-loras` |
+ `None` |
Type: bool |
A2, A3 |
- --lora-use-virtual-experts |
- False |
+ `--lora-use-virtual-experts` |
+ `False` |
bool flag (set to enable) |
A2, A3 |
- --lora-strict-loading |
- False |
+ `--lora-strict-loading` |
+ `False` |
Type: bool |
A2, A3 |
| `--max-lora-chunk-size` |
`16` |
- 16, 32, 64, 128 |
+ `16`, `32`, `64`, `128` |
Special for GPU |
@@ -1209,7 +1209,7 @@ click [Server Arguments](../../advanced_features/server_arguments).
| `--sampling-backend` |
`None` |
- pytorch,
ascend |
+ `pytorch`, `ascend` |
A2, A3 |
@@ -1227,19 +1227,19 @@ click [Server Arguments](../../advanced_features/server_arguments).
| `--dsa-prefill-backend` |
`flashmla_sparse` |
- flashmla_sparse, flashmla_decode,
fa3, tilelang, aiter |
+ `flashmla_sparse`, `flashmla_decode`, `fa3`, `tilelang`, `aiter` |
Special for GPU |
| `--dsa-decode-backend` |
`fa3` |
- flashmla_prefill, flashmla_kv, fa3,
tilelang, aiter |
+ `flashmla_prefill`, `flashmla_kv`, `fa3`, `tilelang`, `aiter` |
Special for GPU |
| `--fp8-gemm-backend` |
`auto` |
- auto, deep_gemm, flashinfer_trtllm,
flashinfer_cutlass,
flashinfer_deepgemm,
cutlass, triton, aiter |
+ `auto`, `deep_gemm`, `flashinfer_trtllm`, `flashinfer_cutlass`, `flashinfer_deepgemm`, `cutlass`, `triton`, `aiter` |
Special for GPU |
@@ -1274,7 +1274,7 @@ click [Server Arguments](../../advanced_features/server_arguments).
| `--speculative-algorithm` |
`None` |
- EAGLE3, NEXTN |
+ `EAGLE3`, `NEXTN` |
A2, A3 |
@@ -1286,13 +1286,13 @@ click [Server Arguments](../../advanced_features/server_arguments).
`--speculative-draft-model-` `revision` |
`None` |
- Type: str, branch name, tag name, commit id |
+ Type: str, `branch name`, `tag name`, `commit id` |
A2, A3 |
| `--speculative-draft-load-format` |
- auto |
- auto, dummy |
+ `auto` |
+ `auto`, `dummy` |
A2, A3 |
@@ -1334,7 +1334,7 @@ click [Server Arguments](../../advanced_features/server_arguments).
`--speculative-attention-` `mode` |
`prefill` |
- prefill, decode |
+ `prefill`, `decode` |
A2, A3 |
@@ -1411,11 +1411,11 @@ click [Server Arguments](../../advanced_features/server_arguments).
`--speculative-ngram-` `match-type` |
`BFS` |
- BFS, PROB |
- Experimental. BFS uses recency-based expansion; PROB uses frequency-based expansion. |
+ `BFS`, `PROB` |
+ Experimental. `BFS` uses recency-based expansion; `PROB` uses frequency-based expansion. |
- --speculative-ngram-
max-trie-depth |
+ `--speculative-ngram-` `max-trie-depth` |
`18` |
Type: int |
Experimental |
@@ -1476,19 +1476,19 @@ click [Server Arguments](../../advanced_features/server_arguments).
| `--moe-a2a-backend` |
`none` |
- none, deepep, ascend_fuseep(It is incompatible with eplb) |
+ `none`, `deepep`, `ascend_fuseep`(It is incompatible with eplb) |
A2, A3 |
| `--moe-runner-backend` |
`auto` |
- auto, triton |
+ `auto`, `triton` |
A2, A3 |
`--flashinfer-mxfp4-` `moe-precision` |
`default` |
- default, bf16 |
+ `default`, `bf16` |
Special for GPU |
@@ -1500,7 +1500,7 @@ click [Server Arguments](../../advanced_features/server_arguments).
| `--deepep-mode` |
`auto` |
- normal,
low_latency, auto |
+ `normal`, `low_latency`, `auto` |
A2, A3 |
@@ -1518,13 +1518,13 @@ click [Server Arguments](../../advanced_features/server_arguments).
| `--ep-dispatch-algorithm` |
`None` |
- static, dynamic, fake |
+ `static`, `dynamic`, `fake` |
A2, A3 |
| `--init-expert-location` |
`trivial` |
- trivial, <path.pt>, <path.json>, <json_string> |
+ `trivial`, `<path.pt>`, `<path.json>`, `<json_string>` |
A2, A3 |
@@ -1535,56 +1535,56 @@ click [Server Arguments](../../advanced_features/server_arguments).
| `--eplb-algorithm` |
- deepseek |
- auto, deepseek |
+ `deepseek` |
+ `auto`, `deepseek` |
A2, A3 |
- --eplb-rebalance-num-iterations |
- 1000 |
+ `--eplb-rebalance-num-iterations` |
+ `1000` |
Type: int |
A2, A3 |
- --eplb-rebalance-layers-
per-chunk |
- None |
+ `--eplb-rebalance-layers-` `per-chunk` |
+ `None` |
Type: int |
A2, A3 |
- --eplb-min-rebalancing-
utilization-threshold |
- 1.0 |
+ `--eplb-min-rebalancing-` `utilization-threshold` |
+ `1.0` |
Type: float |
A2, A3 |
- --expert-distribution-
recorder-mode |
+ `--expert-distribution-` `recorder-mode` |
`None` |
- stat, stat_approx, per_pass, per_token |
+ `stat`, `stat_approx`, `per_pass`, `per_token` |
A2, A3 |
- --expert-distribution-
recorder-buffer-size |
- None |
+ `--expert-distribution-` `recorder-buffer-size` |
+ `None` |
Type: int |
A2, A3 |
- --enable-expert-distribution-
metrics |
- False |
+ `--enable-expert-distribution-` `metrics` |
+ `False` |
bool flag (set to enable) |
A2, A3 |
- --moe-dense-tp-size |
+ `--moe-dense-tp-size` |
`None` |
- 1 |
+ `1` |
A2, A3 |
- --elastic-ep-backend |
+ `--elastic-ep-backend` |
`None` |
- none, mooncake |
+ `none`, `mooncake` |
Special for GPU |
@@ -1624,19 +1624,19 @@ click [Server Arguments](../../advanced_features/server_arguments).
| `--mamba-ssm-dtype` |
`float32` |
- float32,
bfloat16,
float16 |
+ `float32`, `bfloat16`, `float16` |
A2, A3 |
| `--mamba-full-memory-ratio` |
- 0.9 |
+ `0.9` |
Type: float |
A2, A3 |
| `--mamba-scheduler-strategy` |
`auto` |
- auto,
no_buffer,
extra_buffer |
+ `auto`, `no_buffer`, `extra_buffer` |
A2, A3 |
@@ -1689,36 +1689,36 @@ click [Server Arguments](../../advanced_features/server_arguments).
| `--hicache-write-policy` |
`write_through` |
- Currently only write_back supported |
+ Currently only `write_back` supported |
A2, A3 |
- --hicache-io-backend |
- kernel |
- kernel_ascend, direct |
+ `--hicache-io-backend` |
+ `kernel` |
+ `kernel_ascend`, `direct` |
A2, A3 |
- --hicache-mem-layout |
- layer_first |
- page_first_direct, page_first_kv_split |
+ `--hicache-mem-layout` |
+ `layer_first` |
+ `page_first_direct`, `page_first_kv_split` |
A2, A3 |
- --hicache-storage-
backend |
- None |
- file |
+ `--hicache-storage-` `backend` |
+ `None` |
+ `file` |
A2, A3 |
- --hicache-storage-
prefetch-policy |
- timeout |
- best_effort, wait_complete, timeout |
+ `--hicache-storage-` `prefetch-policy` |
+ `timeout` |
+ `best_effort`, `wait_complete`, `timeout` |
Special for GPU |
- --hicache-storage-
backend-extra-config |
- None |
+ `--hicache-storage-` `backend-extra-config` |
+ `None` |
Type: str |
Special for GPU |
@@ -1840,7 +1840,7 @@ click [Server Arguments](../../advanced_features/server_arguments).
| `--offload-mode` |
`cpu` |
- cpu (DeepSeek only)
meta (DeepSeek only)
sharded_gpu (DeepSeek only, only support tp=1 dp>1) |
+ `cpu` (DeepSeek only) `meta` (DeepSeek only) `sharded_gpu` (DeepSeek only, only support tp=1 dp>1) |
A2, A3 |
@@ -1934,254 +1934,248 @@ click [Server Arguments](../../advanced_features/server_arguments).
A2, A3 |
- --disable-tokenizer-
batch-decode |
+ `--disable-tokenizer-` `batch-decode` |
`False` |
bool flag (set to enable) |
A2, A3 |
- --disable-custom-
all-reduce |
+ `--disable-custom-` `all-reduce` |
`False` |
bool flag (set to enable) |
Special for GPU |
- --enable-mscclpp |
+ `--enable-mscclpp` |
`False` |
bool flag (set to enable) |
Special for GPU |
- --enable-torch-
symm-mem |
+ `--enable-torch-` `symm-mem` |
`False` |
bool flag (set to enable) |
Special for GPU |
- --disable-overlap
-schedule |
+ `--disable-overlap` `-schedule` |
`False` |
bool flag (set to enable) |
A2, A3 |
- --enable-mixed-
chunk |
+ `--enable-mixed-` `chunk` |
`False` |
bool flag (set to enable) |
A2, A3 |
- --enable-dp-attention |
+ `--enable-dp-attention` |
`False` |
bool flag (set to enable) |
A2, A3 |
- --enable-dp-attention-local-control-broadcast |
+ `--enable-dp-attention-local-control-broadcast` |
`False` |
bool flag (set to enable) |
A2, A3 |
- --enable-dp-lm-head |
+ `--enable-dp-lm-head` |
`False` |
bool flag (set to enable) |
A2, A3 |
- --enable-two-
batch-overlap |
+ `--enable-two-` `batch-overlap` |
`False` |
bool flag (set to enable) |
Planned |
- --enable-single-
batch-overlap |
+ `--enable-single-` `batch-overlap` |
`False` |
bool flag (set to enable) |
A2, A3 |
- --tbo-token-
distribution-threshold |
- 0.48 |
+ `--tbo-token-` `distribution-threshold` |
+ `0.48` |
Type: float |
Planned |
- --enable-torch-
compile |
- False |
- bool flag (set to enable) |
- A2, A3 |
-
-
- --enable-torch-
compile-debug-mode |
+ `--enable-torch-` `compile` |
`False` |
bool flag (set to enable) |
A2, A3 |
- --enforce-piecewise-
cuda-graph |
+ `--enable-torch-` `compile-debug-mode` |
+ `False` |
+ bool flag (set to enable) |
+ A2, A3 |
+
+
+ `--enforce-piecewise-` `cuda-graph` |
`False` |
bool flag (set to enable); Currently, Llama-3.1-8B-Instruct and Qwen2.5-7B-Instruct models are supported. |
A2, A3 |
- --piecewise-cuda-
graph-tokens |
- None |
+ `--piecewise-cuda-` `graph-tokens` |
+ `None` |
Type: JSON list |
A2, A3 |
- --piecewise-cuda-
graph-compiler |
- eager |
- eager |
+ `--piecewise-cuda-` `graph-compiler` |
+ `eager` |
+ `eager` |
A2, A3 |
- --torch-compile-max-bs |
- 32 |
+ `--torch-compile-max-bs` |
+ `32` |
Type: int |
A2, A3 |
- --piecewise-cuda-
graph-max-tokens |
- None |
+ `--piecewise-cuda-` `graph-max-tokens` |
+ `None` |
Type: int |
A2, A3 |
- --torchao-config |
+ `--torchao-config` |
`` |
Type: str |
Special for GPU |
- --enable-nan-detection |
- False |
- bool flag (set to enable) |
- A2, A3 |
-
-
- --enable-p2p-check |
+ `--enable-p2p-check` |
`False` |
bool flag (set to enable) |
Special for GPU |
- --triton-attention-
reduce-in-fp32 |
+ `--triton-attention-` `reduce-in-fp32` |
`False` |
bool flag (set to enable) |
Special for GPU |
- --triton-attention-
num-kv-splits |
- 8 |
+ `--triton-attention-` `num-kv-splits` |
+ `8` |
Type: int |
Special for GPU |
- --triton-attention-
split-tile-size |
- None |
+ `--triton-attention-` `split-tile-size` |
+ `None` |
Type: int |
Special for GPU |
- --delete-ckpt-
after-loading |
- False |
- bool flag (set to enable) |
- A2, A3 |
-
-
- --enable-memory-saver |
+ `--delete-ckpt-` `after-loading` |
`False` |
bool flag (set to enable) |
A2, A3 |
- --enable-weights-
cpu-backup |
+ `--enable-memory-saver` |
`False` |
bool flag (set to enable) |
A2, A3 |
- --enable-draft-weights-
cpu-backup |
+ `--enable-weights-` `cpu-backup` |
`False` |
bool flag (set to enable) |
A2, A3 |
- --allow-auto-truncate |
+ `--enable-draft-weights-` `cpu-backup` |
`False` |
bool flag (set to enable) |
A2, A3 |
- --enable-custom-
logit-processor |
+ `--allow-auto-truncate` |
`False` |
bool flag (set to enable) |
A2, A3 |
- --flashinfer-mla-
disable-ragged |
+ `--enable-custom-` `logit-processor` |
+ `False` |
+ bool flag (set to enable) |
+ A2, A3 |
+
+
+ `--flashinfer-mla-` `disable-ragged` |
`False` |
bool flag (set to enable) |
Special for GPU |
- --disable-shared-
experts-fusion |
- True |
+ `--disable-shared-` `experts-fusion` |
+ `True` |
bool flag (set to enable) |
A2, A3 |
- --enforce-shared-experts-fusion |
- False |
- bool flag (set to enable) |
- A2, A3 |
-
-
- --disable-chunked-
prefix-cache |
- True |
- bool flag (set to enable) |
- A2, A3 |
-
-
- --disable-fast-
image-processor |
+ `--enforce-shared-experts-fusion` |
`False` |
bool flag (set to enable) |
A2, A3 |
- --keep-mm-feature-
on-device |
+ `--disable-chunked-` `prefix-cache` |
+ `True` |
+ bool flag (set to enable) |
+ A2, A3 |
+
+
+ `--disable-fast-` `image-processor` |
`False` |
bool flag (set to enable) |
A2, A3 |
- --enable-return-
hidden-states |
+ `--keep-mm-feature-` `on-device` |
`False` |
bool flag (set to enable) |
A2, A3 |
- --enable-return-
routed-experts |
+ `--enable-return-` `hidden-states` |
`False` |
bool flag (set to enable) |
A2, A3 |
- --scheduler-recv-
interval |
- 1 |
+ `--enable-return-` `routed-experts` |
+ `False` |
+ bool flag (set to enable) |
+ A2, A3 |
+
+
+ `--scheduler-recv-` `interval` |
+ `1` |
Type: int |
A2, A3 |
- --numa-node |
- None |
+ `--numa-node` |
+ `None` |
List[int] |
A2, A3 |
- --enable-deterministic-
inference |
- False |
+ `--enable-deterministic-` `inference` |
+ `False` |
bool flag (set to enable) |
Planned |
@@ -2345,7 +2339,7 @@ click [Server Arguments](../../advanced_features/server_arguments).
| `--disaggregation-mode` |
`null` |
- null, prefill, decode |
+ `null`, `prefill`, `decode` |
A2, A3 |
@@ -2361,26 +2355,26 @@ click [Server Arguments](../../advanced_features/server_arguments).
| A2, A3 |
- --disaggregation-ib-device |
+ `--disaggregation-ib-device` |
`None` |
Type: str |
Special for GPU |
- --disaggregation-decode-
enable-offload-kvcache |
- False |
- False |
+ `--disaggregation-decode-` `enable-offload-kvcache` |
+ `False` |
+ bool flag (set to enable) |
A2, A3 |
- --num-reserved-decode-tokens |
- 512 |
+ `--num-reserved-decode-tokens` |
+ `512` |
Type: int |
A2, A3 |
- --disaggregation-decode-
polling-interval |
- 1 |
+ `--disaggregation-decode-` `polling-interval` |
+ `1` |
Type: int |
A2, A3 |
@@ -2407,27 +2401,27 @@ click [Server Arguments](../../advanced_features/server_arguments).
- --enable-adaptive-dispatch-to-encoder |
+ `--enable-adaptive-dispatch-to-encoder` |
`False` |
bool flag (set to enable adaptively dispatch) |
A2, A3 |
- --encoder-only |
+ `--encoder-only` |
`False` |
bool flag (set to launch an encoder-only server) |
A2, A3 |
- --language-only |
- False |
+ `--language-only` |
+ `False` |
bool flag (set to load weights for the language model only) |
A2, A3 |
- --encoder-transfer-backend |
- zmq_to_scheduler |
- zmq_to_scheduler, zmq_to_tokenizer, mooncake |
+ `--encoder-transfer-backend` |
+ `zmq_to_scheduler` |
+ `zmq_to_scheduler`, `zmq_to_tokenizer`, `mooncake` |
A2, A3 |
@@ -2504,7 +2498,7 @@ click [Server Arguments](../../advanced_features/server_arguments).
`--remote-instance-weight-` `loader-backend` |
`nccl` |
- transfer_engine, nccl |
+ `transfer_engine`, `nccl` |
Special for GPU |
@@ -2577,25 +2571,25 @@ click [Server Arguments](../../advanced_features/server_arguments).
- --enable-broadcast-mm-
inputs-process |
- False |
- bool flag (set to enable) |
- A2, A3 |
-
-
- --mm-process-config |
- None |
- Type: JSON / Dict |
- A2, A3 |
-
-
- --mm-enable-dp-encoder |
+ `--enable-broadcast-mm-` `inputs-process` |
`False` |
bool flag (set to enable) |
A2, A3 |
- --limit-mm-data-per-request |
+ `--mm-process-config` |
+ `None` |
+ Type: JSON / Dict |
+ A2, A3 |
+
+
+ | `--mm-enable-dp-encoder` |
+ `False` |
+ bool flag (set to enable) |
+ A2, A3 |
+
+
+ | `--limit-mm-data-per-request` |
`None` |
Type: JSON / Dict |
A2, A3 |
@@ -2664,8 +2658,8 @@ click [Server Arguments](../../advanced_features/server_arguments).
- --forward-hooks |
- None |
+ `--forward-hooks` |
+ `None` |
Type: JSON list |
A2, A3 |
@@ -2692,7 +2686,7 @@ click [Server Arguments](../../advanced_features/server_arguments).
- --config |
+ `--config` |
`None` |
Type: str |
A2, A3 |
@@ -2774,8 +2768,8 @@ The following parameters have some functional deficiencies on community
- --tool-server |
- None |
+ `--tool-server` |
+ `None` |
Type: str |