zhaozx-cn b9a0a75c78 fix qwen torchair attention PrefillCacheHit (#2787) ...

### What this PR does / why we need it?
Fix qwen torchair attention PrefillCacheHit 
### Does this PR introduce _any_ user-facing change?

### How was this patch tested?
vLLM version: v0.10.1.1
vLLM main:
e599e2c65e

- vLLM version: main
- vLLM main:
0b9a612fa3

Signed-off-by: zhaozixin <zhaozixin1@huawei.com>
Co-authored-by: zhaozixin <zhaozixin1@huawei.com>

2025-09-11 14:26:59 +08:00

..

attention

Added support for KV connector v1 (#2039)

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

compilation

[Bugfix] Fix aclgraph not enabled by default (#2590)

2025-08-28 14:08:31 +08:00

core

[main] add pd transfer for ascend scheduler (#2753)

2025-09-10 08:46:39 +08:00

device_allocator

[Misc]Clean up useless import from vllm (#2049)

2025-07-28 16:01:59 +08:00

distributed

LLMdatadist connector adapt the distributed KV aggregation (#2718)

2025-09-11 11:37:41 +08:00

lora

[Misc] Move lora patch file into lora module (#2797)

2025-09-08 21:42:12 +08:00

models

[main] adjust the position of warm_up_atb (#2823)

2025-09-10 14:06:38 +08:00

multistream

[Quickfix] update CachedRequestState as NewRequestData changed (#2367)

2025-08-15 07:35:27 +08:00

ops

[Feat] Unquantized linear nz support (#2619)

2025-09-11 11:40:00 +08:00

patch

[Fix] Fix SharedFusedMoE (#2817)

2025-09-09 18:19:56 +08:00

quantization

[Feat] Unquantized linear nz support (#2619)

2025-09-11 11:40:00 +08:00

sample

[main] add pd transfer for ascend scheduler (#2753)

2025-09-10 08:46:39 +08:00

spec_decode

[FEATURE][MTP] Support MTP > 1 (#2708)

2025-09-05 09:11:22 +08:00

torchair

fix qwen torchair attention PrefillCacheHit (#2787)

2025-09-11 14:26:59 +08:00

worker

[main] adjust the position of warm_up_atb (#2823)

2025-09-10 14:06:38 +08:00

__init__.py

Bump torch version to 2.7.1 (#1562)

2025-08-05 08:43:24 +08:00

ascend_config.py

[feat]: oproj tensor parallelism in pure DP and graph-mode scenarios. (#2167)

2025-09-07 10:31:32 +08:00

ascend_forward_context.py

[main] Optimize rope in Qwen Models (#2571)

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

envs.py

[main] flashcomm_v1 optim in Qwen Dense Models (#2802)

2025-09-08 22:52:24 +08:00

meta_registration.py

Fix some ci issue and refactor modelrunner (#2445)

2025-08-20 09:01:04 +08:00

platform.py

[Misc] Move lora patch file into lora module (#2797)

2025-09-08 21:42:12 +08:00

utils.py

[CI/UT] Fix UTs on register customop and warm up model (#2862)

2025-09-11 11:30:16 +08:00