wangxiyuan 2ae0bad96d Remove VLLM_ASCEND_ENABLE_DENSE_OPTIMIZE (#5272) ...

`VLLM_ASCEND_ENABLE_DENSE_OPTIMIZE` is only used together with
`VLLM_ASCEND_ENABLE_PREFETCH_MLP` which is useless totally. This PR
remove it.
- vLLM version: release/v0.13.0
- vLLM main:
ad32e3e19c

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>

2025-12-25 11:09:56 +08:00

..

310p.md

[Doc] Update tutorial index (#4920)

2025-12-11 20:53:13 +08:00

DeepSeek-R1.md

【Doc】Deepseekv3.1/R1 doc enhancement (#4827)

2025-12-19 10:52:33 +08:00

DeepSeek-V3.1.md

[Doc] Update the weight download URL. (#5238)

2025-12-23 08:53:30 +08:00

DeepSeek-V3.2.md

[Doc] Update the weight download URL. (#5238)

2025-12-23 08:53:30 +08:00

index.md

Add Qwen3-VL-235B-A22B-Instruct tutorials (#5167)

2025-12-19 14:56:17 +08:00

Kimi-K2-Thinking.md

[Doc] Update tutorial index (#4920)

2025-12-11 20:53:13 +08:00

pd_disaggregation_mooncake_multi_node.md

[Doc][P/D] Fix MooncakeConnector's name (#5172)

2025-12-18 22:29:19 +08:00

pd_disaggregation_mooncake_single_node.md

[Doc][P/D] Fix MooncakeConnector's name (#5172)

2025-12-18 22:29:19 +08:00

Qwen2.5-7B.md

[Doc] Upgrade some outdated doc (#5062)

2025-12-16 11:48:19 +08:00

Qwen2.5-Omni.md

[Doc] Upgrade some outdated doc (#5062)

2025-12-16 11:48:19 +08:00

Qwen3_embedding.md

[Doc] add qwen3 reranker (#5086)

2025-12-18 10:54:07 +08:00

Qwen3_reranker.md

[Doc] add qwen3 reranker (#5086)

2025-12-18 10:54:07 +08:00

Qwen3-8B-W4A8.md

[Doc] Upgrade some outdated doc (#5062)

2025-12-16 11:48:19 +08:00

Qwen3-30B-A3B.md

[Doc] Update tutorial index (#4920)

2025-12-11 20:53:13 +08:00

Qwen3-32B-W4A4.md

[doc]Modify quantization tutorials (#5026)

2025-12-15 20:12:06 +08:00

Qwen3-235B-A22B.md

[Doc] fix docs set rope_theta value is 10e6 in qwen3-235b model (#5258)

2025-12-23 10:21:46 +08:00

Qwen3-Coder-30B-A3B.md

[Doc] Add tutorial for Qwen3-Coder-30B-A3B (#4391)

2025-12-02 16:03:37 +08:00

Qwen3-Dense.md

Remove VLLM_ASCEND_ENABLE_DENSE_OPTIMIZE (#5272)

2025-12-25 11:09:56 +08:00

Qwen3-Next.md

Qwen3-Next：Update the gpu-memory-utilization parameter to 0.7 (#5129)

2025-12-18 15:16:33 +08:00

Qwen3-VL-235B-A22B-Instruct.md

Add Qwen3-VL-235B-A22B-Instruct tutorials (#5167)

2025-12-19 14:56:17 +08:00

Qwen-VL-Dense.md

[doc][main] Correct mistakes in doc (#4945)

2025-12-12 19:17:10 +08:00

ray.md

[doc][main] Correct more doc mistakes (#4958)

2025-12-13 18:36:58 +08:00