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 a8ab43b80..dfcbc451b 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
@@ -173,6 +173,58 @@ click [Server Arguments](../../advanced_features/server_arguments).
+## SSL/TLS
+
+
+
+
+
+
+
+
+
+
+
+ | Argument |
+ Defaults |
+ Options |
+ Server supported |
+
+
+
+
+ | `--ssl-keyfile` |
+ `None` |
+ Type: str |
+ A2, A3 |
+
+
+ | `--ssl-certfile` |
+ `None` |
+ Type: str |
+ A2, A3 |
+
+
+ | `--ssl-keyfile-password` |
+ `None` |
+ Type: str |
+ A2, A3 |
+
+
+ | `--enable-ssl-refresh` |
+ `False` |
+ bool flag (set to enable) |
+ A2, A3 |
+
+
+ | `--enable-http2` |
+ `False` |
+ bool flag (set to enable) |
+ A2, A3 |
+
+
+
+
## Quantization and data type
@@ -335,6 +387,18 @@ click [Server Arguments](../../advanced_features/server_arguments).
bool flag (set to enable) |
A2, A3 |
+
+ | `--disable-priority-preemption` |
+ `False` |
+ bool flag (set to enable) |
+ A2, A3 |
+
+
+ | `--default-priority-value` |
+ `None` |
+ Type: int |
+ A2, A3 |
+
`--schedule-low-priority-` `values-first` |
`False` |
@@ -495,6 +559,18 @@ click [Server Arguments](../../advanced_features/server_arguments).
bool flag (set to enable) |
A2, A3 |
+
+ --stream-response-default-include-usage |
+ False |
+ bool flag (set to enable) |
+ A2, A3 |
+
+
+ --enable-streaming-session |
+ False |
+ bool flag (set to enable) |
+ A2, A3 |
+
--random-seed |
None |
@@ -561,6 +637,18 @@ click [Server Arguments](../../advanced_features/server_arguments).
bool flag (set to enable) |
A2, A3 |
+
+ --use-ray |
+ False |
+ bool flag (set to enable) |
+ A2, A3 |
+
+
+ --custom-sigquit-handler |
+ None |
+ Only for engine |
+ A2, A3 |
+
@@ -626,6 +714,12 @@ click [Server Arguments](../../advanced_features/server_arguments).
bool flag (set to enable) |
A2, A3 |
+
+ | `--enable-mfu-metrics` |
+ `False` |
+ bool flag (set to enable) |
+ A2, A3 |
+
`--enable-metrics-for-` `all-schedulers` |
`False` |
@@ -644,6 +738,12 @@ click [Server Arguments](../../advanced_features/server_arguments).
List[str] |
A2, A3 |
+
+ | `--extra-metric-labels` |
+ `None` |
+ Type: JSON/Dict |
+ A2, A3 |
+
`--bucket-time-to-` `first-token` |
`None` |
@@ -826,6 +926,12 @@ click [Server Arguments](../../advanced_features/server_arguments).
Type: str |
A2, A3 |
+
+ --file-storage-path |
+ sglang_storage |
+ Type: str |
+ Unused reserved parameter |
+
--enable-cache-report |
False |
@@ -1035,6 +1141,24 @@ click [Server Arguments](../../advanced_features/server_arguments).
triton,<br/>csgmv,<br/>ascend,<br/>torch_native |
A2, A3 |
+
+ --experts-shared-outer-loras |
+ None |
+ Type: bool |
+ A2, A3 |
+
+
+ --lora-use-virtual-experts |
+ False |
+ bool flag (set to enable) |
+ A2, A3 |
+
+
+ --lora-strict-loading |
+ False |
+ Type: bool |
+ A2, A3 |
+
| `--max-lora-chunk-size` |
`16` |
@@ -1302,6 +1426,24 @@ click [Server Arguments](../../advanced_features/server_arguments).
Type: int |
Experimental |
+
+ | `--speculative-ngram-external-corpus-path` |
+ `None` |
+ Type: str |
+ Experimental |
+
+
+ | `--speculative-ngram-external-sam-budget` |
+ `0` |
+ Type: int |
+ Experimental |
+
+
+ | `--speculative-ngram-external-corpus-max-tokens` |
+ `10000000` |
+ Type: int |
+ Experimental |
+
@@ -1612,6 +1754,40 @@ click [Server Arguments](../../advanced_features/server_arguments).
+## Diffusion LLM
+
+
+
+
+
+
+
+
+
+
+
+ | Argument |
+ Defaults |
+ Options |
+ Server supported |
+
+
+
+
+ | `--dllm-algorithm` |
+ `None` |
+ Type: str |
+ A2, A3 |
+
+
+ | `--dllm-algorithm-config` |
+ `None` |
+ Type: str |
+ A2, A3 |
+
+
+
+
## Offloading (must be used with `--disable-cuda-graph`)
@@ -1821,6 +1997,12 @@ click [Server Arguments](../../advanced_features/server_arguments).
bool flag (set to enable) |
A2, A3 |
+
+ --enable-dp-attention-local-control-broadcast |
+ `False` |
+ bool flag (set to enable) |
+ A2, A3 |
+
--enable-dp-lm-head |
`False` |
@@ -1971,6 +2153,12 @@ click [Server Arguments](../../advanced_features/server_arguments).
bool flag (set to enable) |
A2, A3 |
+
+ --enforce-shared-experts-fusion |
+ False |
+ bool flag (set to enable) |
+ A2, A3 |
+
--disable-chunked-<br/>prefix-cache |
True |
@@ -2043,12 +2231,36 @@ click [Server Arguments](../../advanced_features/server_arguments).
bool flag (set to enable) |
A2, A3 |
+
+ | `--enable-prefill-context-parallel` |
+ `False` |
+ bool flag (set to enable) |
+ A2, A3 |
+
+
+ | `--prefill-cp-mode` |
+ `in-seq-split` |
+ Type: str |
+ A2, A3 |
+
`--enable-fused-qk-` `norm-rope` |
`False` |
bool flag (set to enable) |
Special for GPU |
+
+ | `--enable-precise-embedding-interpolation` |
+ `False` |
+ bool flag (set to enable) |
+ A2, A3 |
+
+
+ | `--gc-threshold` |
+ `None` |
+ List[int] |
+ A2, A3 |
+
@@ -2281,6 +2493,18 @@ click [Server Arguments](../../advanced_features/server_arguments).
bool flag (set to enable) |
A2, A3 |
+
+ | `--weight-loader-prefetch-checkpoints` |
+ `False` |
+ bool flag (set to enable) |
+ A2, A3 |
+
+
+ | `--weight-loader-prefetch-num-threads` |
+ `4` |
+ Type: int |
+ A2, A3 |
+
`--remote-instance-weight-` `loader-seed-instance-ip` |
`None` |
diff --git a/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_support_models.mdx b/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_support_models.mdx
index 728346d74..d7ef03691 100644
--- a/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_support_models.mdx
+++ b/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_support_models.mdx
@@ -49,6 +49,12 @@ You are welcome to enable various models based on your business requirements.
✅ |
✅ |
+
+ | Qwen/Qwen3.5-397B-A17B |
+ Qwen |
+ ✅ |
+ ✅ |
+
| Qwen/Qwen3-30B-A3B-Instruct-2507 |
Qwen |
@@ -265,6 +271,12 @@ You are welcome to enable various models based on your business requirements.
✅ |
✅ |
+
+ | moonshotai/Kimi-Linear-48B-A3B-Instruct |
+ Kimi Linear (48B-A3B) |
+ ✅ |
+ ✅ |
+
| eigen-ai-labs/gpt-oss-120b-bf16 |
GPTOSS |
@@ -289,6 +301,12 @@ You are welcome to enable various models based on your business requirements.
✅ |
✅ |
+
+ | FLM/Tele-FLM |
+ Tele FLM (52B-1T) |
+ ✅ |
+ ✅ |
+
| bigcode/starcoder2-7b |
StarCoder2 |
@@ -301,6 +319,18 @@ You are welcome to enable various models based on your business requirements.
✅ |
✅ |
+
+ | OrionStarAI/Orion-14B-Base |
+ Orion (14B) |
+ ✅ |
+ ✅ |
+
+
+ | EleutherAI/gpt-j-6b |
+ GPT-J (6B) |
+ ✅ |
+ ✅ |
+
@@ -454,6 +484,63 @@ You are welcome to enable various models based on your business requirements.
✅ |
✅ |
+
+ | PaddlePaddle/ERNIE-4.5-VL-28B-A3B-PT |
+ Ernie4.5-VL |
+ ✅ |
+ ✅ |
+
+
+ | Qwen/Qwen3-Omni-30B-A3B-Instruct |
+ Qwen3-Omni |
+ ✅ |
+ ✅ |
+
+
+ | stepfun-ai/Step3-VL-10B |
+ Step3-VL (10B) |
+ ✅ |
+ ✅ |
+
+
+
+
+## Diffusion language models
+
+
+
+
+
+
+
+
+
+
+ | Models |
+ Model Family |
+ A2 Supported |
+ A3 Supported |
+
+
+
+
+ | inclusionAI/LLaDA2.0-flash |
+ LLaDA2.0 (mini, flash) |
+ ✅ |
+ ✅ |
+
+
+ | JetLM/SDAR-8B-Chat |
+ SDAR (JetLM) |
+ ✅ |
+ ✅ |
+
+
+ | JetLM/SDAR-30B-A3B-Chat |
+ SDAR (JetLM) |
+ ✅ |
+ ✅ |
+
@@ -589,5 +676,17 @@ You are welcome to enable various models based on your business requirements.
✅ |
✅ |
+
+ | Qwen/Qwen3-Reranker-8B |
+ Qwen3-Reranker (decoder-only yes/no) |
+ ✅ |
+ ✅ |
+
+
+ | Qwen/Qwen3-VL-Reranker-2B |
+ Qwen3-VL-Reranker (multimodal yes/no) |
+ ✅ |
+ ✅ |
+