LeeWenquan f4e3d22432 Remove chunked_prefill_for_mla and fix ring_mla bug (#2781) ...

### What this PR does / why we need it?
Remove chunked prefill for mla branch in mla , and change dtype of
prefill_mask to avoid accuracy problem
### Does this PR introduce _any_ user-facing change?
NO
### How was this patch tested?

- vLLM version: v0.10.2
- vLLM main:
ef7eefe17a

---------

Signed-off-by: SunnyLee219 <3294305115@qq.com>

2025-09-18 19:43:26 +08:00

..

_templates/sections

[Doc] add v0.9.1 release note (#2646)

2025-09-03 18:04:27 +08:00

assets

[Doc] Support kimi-k2-w8a8 (#2162)

2025-08-06 19:28:47 +08:00

community

[Release] Add release note for v0.10.2rc1 (#2921)

2025-09-16 01:20:05 +08:00

developer_guide

[Doc] Update accuracy reports for v0.10.1rc1 (#2755)

2025-09-04 22:17:17 +08:00

locale/zh_CN/LC_MESSAGES

Remove chunked_prefill_for_mla and fix ring_mla bug (#2781)

2025-09-18 19:43:26 +08:00

logos

[Doc] Add sphinx build for vllm-ascend (#55)

2025-02-13 18:44:17 +08:00

tutorials

[Doc] Add multi-node ray backend tutorial (#2376)

2025-09-18 15:30:18 +08:00

user_guide

Remove chunked_prefill_for_mla and fix ring_mla bug (#2781)

2025-09-18 19:43:26 +08:00

conf.py

[Release] Add release note for v0.10.2rc1 (#2921)

2025-09-16 01:20:05 +08:00

faqs.md

[Release] Add release note for v0.10.2rc1 (#2921)

2025-09-16 01:20:05 +08:00

index.md

[Doc] Update user doc index (#1581)

2025-07-10 14:26:59 +08:00

installation.md

Revert "Upgrade CANN version to 8.3.rc1.alpha001 (#2903)" (#2909)

2025-09-13 16:21:54 +08:00

quick_start.md

[ReleaseNote] Release note of v0.10.0rc1 (#2225)

2025-08-07 14:46:49 +08:00