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 63efb4f1c..ca10c07bb 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
@@ -46,12 +46,24 @@ click [Server Arguments](../../advanced_features/server_arguments).
`auto`, `slow` |
A2, A3 |
+
+ | `--tokenizer-backend` |
+ `huggingface` |
+ `huggingface`, `fastokens` |
+ A2, A3 |
+
| `--tokenizer-worker-num` |
`1` |
Type: int |
A2, A3 |
+
+ | `--detokenizer-worker-num` |
+ `1` |
+ Type: int |
+ A2, A3 |
+
| `--skip-tokenizer-init` |
`False` |
@@ -106,6 +118,12 @@ click [Server Arguments](../../advanced_features/server_arguments).
`auto`, `sglang`, `transformers` |
A2, A3 |
+
+ | `--model-config-parser` |
+ `auto` |
+ Type: str |
+ A2, A3 |
+
@@ -471,6 +489,18 @@ click [Server Arguments](../../advanced_features/server_arguments).
List[float] |
A2, A3 |
+
+ | `--prefill-delayer-queue-min-ratio` |
+ `None` |
+ Type: float |
+ A2, A3 |
+
+
+ | `--prefill-delayer-max-delay-ms` |
+ `None` |
+ Type: float |
+ A2, A3 |
+
`--abort-on-priority-` `when-disabled` |
`False` |
@@ -553,6 +583,12 @@ click [Server Arguments](../../advanced_features/server_arguments).
Type: int |
A2, A3 |
+
+ | `--batch-notify-size` |
+ `16` |
+ Type: int |
+ A2, A3 |
+
| `--incremental-streaming-output` |
`False` |
@@ -637,6 +673,12 @@ click [Server Arguments](../../advanced_features/server_arguments).
bool flag (set to enable) |
A2, A3 |
+
+ | `--load-snapshot-publish-interval` |
+ `15` |
+ Type: int |
+ A2, A3 |
+
| `--use-ray` |
`False` |
@@ -804,6 +846,24 @@ click [Server Arguments](../../advanced_features/server_arguments).
Type: str |
Special for GPU |
+
+ | `--enable-forward-pass-metrics` |
+ `False` |
+ bool flag (set to enable) |
+ A2, A3 |
+
+
+ | `--forward-pass-metrics-worker-id` |
+ `` |
+ Type: str |
+ A2, A3 |
+
+
+ | `--forward-pass-metrics-ipc-name` |
+ `None` |
+ Type: str |
+ A2, A3 |
+
| `--enable-trace` |
`False` |
@@ -811,7 +871,13 @@ click [Server Arguments](../../advanced_features/server_arguments).
A2, A3 |
- | `--oltp-traces-endpoint` |
+ `--trace-modules` |
+ `request` |
+ Type: str |
+ A2, A3 |
+
+
+ | `--otlp-traces-endpoint` |
`localhost:4317` |
Type: str |
A2, A3 |
@@ -944,6 +1010,18 @@ click [Server Arguments](../../advanced_features/server_arguments).
`deepseek-r1` `deepseek-v3` `glm45` `gpt-oss` `kimi` `qwen3` `qwen3-thinking` `step3` |
A2, A3 |
+
+ | `--strip-thinking-cache` |
+ `False` |
+ bool flag (set to enable) |
+ A2, A3 |
+
+
+ | `--enable-strict-thinking` |
+ `False` |
+ bool flag (set to enable) |
+ A2, A3 |
+
| `--tool-call-parser` |
`None` |
@@ -956,6 +1034,18 @@ click [Server Arguments](../../advanced_features/server_arguments).
`openai`, `model` |
A2, A3 |
+
+ | `--asr-max-buffer-seconds` |
+ `60` |
+ Type: int |
+ A2, A3 |
+
+
+ | `--asr-max-concurrent-sessions` |
+ `32` |
+ Type: int |
+ A2, A3 |
+
@@ -1159,6 +1249,12 @@ click [Server Arguments](../../advanced_features/server_arguments).
Type: bool |
A2, A3 |
+
+ | `--lora-drain-wait-threshold` |
+ `0.0` |
+ Type: float |
+ A2, A3 |
+
| `--max-lora-chunk-size` |
`16` |
@@ -1313,6 +1409,12 @@ click [Server Arguments](../../advanced_features/server_arguments).
Type: int |
A2, A3 |
+
+ | `--speculative-dflash-block-size` |
+ `None` |
+ Type: int |
+ A2, A3 |
+
`--speculative-accept-` `threshold-single` |
`1.0` |
@@ -1355,6 +1457,12 @@ click [Server Arguments](../../advanced_features/server_arguments).
`ascend` |
A2, A3 |
+
+ `--speculative-dflash-draft-window-size` `--speculative-draft-window-size` |
+ `None` |
+ Type: int |
+ A2, A3 |
+
| `--speculative-draft-model-quantization` |
`None` |
@@ -1444,6 +1552,24 @@ click [Server Arguments](../../advanced_features/server_arguments).
Type: int |
Experimental |
+
+ | `--speculative-adaptive` |
+ `False` |
+ bool flag (set to enable) |
+ A2, A3 |
+
+
+ | `--speculative-adaptive-config` |
+ `None` |
+ Type: str |
+ A2, A3 |
+
+
+ | `--speculative-skip-dp-mlp-sync` |
+ `False` |
+ bool flag (set to enable) |
+ A2, A3 |
+
@@ -1503,6 +1629,12 @@ click [Server Arguments](../../advanced_features/server_arguments).
`normal`, `low_latency`, `auto` |
A2, A3 |
+
+ | `--deepep-dispatcher-output-dtype` |
+ `auto` |
+ `auto`, `bf16`, `fp8`, `int8`, `nvfp4` |
+ A2, A3 |
+
| `--deepep-config` |
`None` |
@@ -1593,6 +1725,12 @@ click [Server Arguments](../../advanced_features/server_arguments).
Type: str |
Special for GPU |
+
+ | `--enable-deepep-waterfill` |
+ `False` |
+ bool flag (set to enable) |
+ A2, A3 |
+
@@ -1708,7 +1846,7 @@ click [Server Arguments](../../advanced_features/server_arguments).
`--hicache-storage-` `backend` |
`None` |
`file` |
- A2, A3 |
+ Planned |
`--hicache-storage-` `prefetch-policy` |
@@ -1885,6 +2023,12 @@ click [Server Arguments](../../advanced_features/server_arguments).
List[int] |
A2, A3 |
+
+ | `--disable-piecewise-cuda-graph` |
+ `False` |
+ bool flag (set to enable) |
+ A2, A3 |
+
| `--disable-cuda-graph` |
`False` |
@@ -1951,6 +2095,12 @@ click [Server Arguments](../../advanced_features/server_arguments).
bool flag (set to enable) |
Special for GPU |
+
+ | `--pre-warm-nccl` |
+ `False` |
+ bool flag (set to enable) |
+ A2, A3 |
+
`--enable-torch-` `symm-mem` |
`False` |
@@ -1997,7 +2147,7 @@ click [Server Arguments](../../advanced_features/server_arguments).
`--enable-single-` `batch-overlap` |
`False` |
bool flag (set to enable) |
- A2, A3 |
+ Special for GPU |
`--tbo-token-` `distribution-threshold` |
@@ -2185,6 +2335,18 @@ click [Server Arguments](../../advanced_features/server_arguments).
`fsdp` |
Planned |
+
+ | `--disable-attn-tp-gather` |
+ `False` |
+ bool flag (set to enable) |
+ A2, A3 |
+
+
+ | `--enable-nsa-prefill-context-parallel` |
+ `False` |
+ bool flag (set to enable) |
+ A2, A3 |
+
`--enable-layerwise-` `nvtx-marker` |
`False` |
@@ -2209,6 +2371,12 @@ click [Server Arguments](../../advanced_features/server_arguments).
bool flag (set to enable) |
A2, A3 |
+
+ | `--dsa-prefill-cp-mode` |
+ `round-robin-split` |
+ `in-seq-split`, `round-robin-split` |
+ A2, A3 |
+
| `--prefill-cp-mode` |
`in-seq-split` |
@@ -2378,6 +2546,12 @@ click [Server Arguments](../../advanced_features/server_arguments).
Type: int |
A2, A3 |
+
+ | `--optimistic-prefill-retries` |
+ `0` |
+ Type: int |
+ A2, A3 |
+
@@ -2501,6 +2675,12 @@ click [Server Arguments](../../advanced_features/server_arguments).
`transfer_engine`, `nccl` |
Special for GPU |
+
+ | `--weight-loader-drop-cache-after-load` |
+ `False` |
+ bool flag (set to enable) |
+ A2, A3 |
+
`--remote-instance-weight-` `loader-start-seed-via-transfer-engine` |
`False` |
@@ -2663,6 +2843,40 @@ click [Server Arguments](../../advanced_features/server_arguments).
Type: JSON list |
A2, A3 |
+
+ | `--enable-quant-communications` |
+ `False` |
+ bool flag (set to enable) |
+ A2, A3 |
+
+
+
+
+## msProbe
+
+
+
+
+
+
+
+
+
+
+
+ | Argument |
+ Defaults |
+ Options |
+ Server supported |
+
+
+
+
+ | `--msprobe-dump-config` |
+ `None` |
+ Type: str |
+ A2, A3 |
+