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 34060ffe0..d022fe465 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 @@ -565,18 +565,6 @@ click [Server Arguments](../../advanced_features/server_arguments). Type: int Planned - - `--enable-prefill-cp` - `False` - bool flag (set to enable) - A2, A3 - - - `--cp-strategy` - `None` - `zigzag`, `interleave` - A2, A3 - `--pp-max-micro-batch-size` `None` @@ -2038,13 +2026,13 @@ click [Server Arguments](../../advanced_features/server_arguments). `--cuda-graph-backend-decode` `None` - `full`,
`breakable`,
`tc_piecewise`,
`disabled` + `full`,
`disabled` A2, A3 `--cuda-graph-backend-prefill` `None` - `breakable`,
`tc_piecewise`,
`disabled` + `disabled` A2, A3 @@ -2419,6 +2407,18 @@ click [Server Arguments](../../advanced_features/server_arguments). bool flag
(set to enable) Experimental + + `--enable-prefill-cp` + `False` + bool flag (set to enable) + A2, A3 + + + `--cp-strategy` + `None` + `zigzag` + A2, A3 + `--enable-fused-qk-`
`norm-rope` `False` 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 ccbb9fd7d..1bbae4554 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 @@ -62,7 +62,7 @@ You are welcome to enable various models based on your business requirements. ✅ - Eco-Tech/Qwen3.6-35B-A3B-w8a8 + Eco-Tech/Qwen3.6-35B-A3B Qwen3.6 ✅ ✅ @@ -74,7 +74,7 @@ You are welcome to enable various models based on your business requirements. ✅ - Eco-Tech/Qwen3.5-397B-A17B-w8a8-mtp + Eco-Tech/Qwen3.5-397B-A17B-w4a8-mtp Qwen3.5 ✅ ✅ @@ -361,12 +361,6 @@ 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 @@ -580,12 +574,6 @@ 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