wangxiaoteng888 ca05f7d632 [Bugfix] TP size larger than KV cache head causes accuracy issues (#3366) ...

### What this PR does / why we need it?
Resolve the issue where, in the case of unequal TP (Tensor Parallelism),
the TP size is larger than the number of model attention kvcache heads,
causing the KV cache to generate duplicates, which leads to transmission
errors in the original code.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
By ci
- vLLM version: v0.11.0rc3
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0

---------

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>
Signed-off-by: wangxiaoteng <wangxiaoteng@huawei.com>
Co-authored-by: nwpu-zxr <zhouxuerong2@huawei.com>

2025-10-11 11:22:23 +08:00

..

device_communicators

[Test] Add ut for files in /distributed (#1951)

2025-07-24 10:36:11 +08:00

test_communicator.py

[2/N][Feat] Add MC2 communication method for MoE layers (#2469)

2025-08-26 19:05:23 +08:00

test_determin_expert_map_all.py

Dynamic Expert Load Balance with Zero-like-overhead (#2956)

2025-09-17 10:36:43 +08:00

test_parallel_state.py

[Bugfix] TP size larger than KV cache head causes accuracy issues (#3366)

2025-10-11 11:22:23 +08:00