Wang Yixuan a7b40b09eb [BugFix]fix deepseek torchair recompile (#3678) ...

### What this PR does / why we need it?
The #3624 PR fix the precision of deepseek torchair, but don't consider
the limitation of torch compile which results in the recompile, This PR
fixs this problem

### Does this PR introduce _any_ user-facing change?
No

### How was this patch tested?

- vLLM version: v0.11.0rc3
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0

Signed-off-by: hust17yixuan <303660421@qq.com>

2025-10-23 22:53:01 +08:00

..

models

perf : optimize memory for deepseek mtp (#2713)

2025-10-23 15:52:17 +08:00

ops

[BugFix]fix deepseek torchair recompile (#3678)

2025-10-23 22:53:01 +08:00

quantization

[Feat][quantization] Support new version w4a8 dynamic quantization for Linear layers (#3311)

2025-10-21 20:18:39 +08:00

__init__.py

[1/4][Refactor] Refactor torchair worker (#1885)

2025-07-21 11:50:46 +08:00

torchair_attention.py

[Feat][Graph] Support FULL_DECODE_ONLY mode for GQA/MHA models (#2128)

2025-09-22 17:14:28 +08:00

torchair_mla.py

fix : support chunked_prefill with deepseek_mtp (#2711)

2025-10-22 11:52:27 +08:00

torchair_model_runner.py

[BugFix]Fix mtp torchair bug caused by #2719 (#3566)

2025-10-21 22:21:44 +08:00

torchair_sfa.py

[Refactor] Adapt deepseek-v3.2 to vllm 0.11.0 (#3432)

2025-10-15 17:48:58 +08:00

torchair_worker.py

[CI] Upgrade vllm to newest commit (#3182)

2025-09-26 06:18:15 +08:00

utils.py

[BugFix] fix deepseek torchair precision (#3624)

2025-10-23 15:41:50 +08:00