LI SHENGYONG 0151022ab8 [bugfix] dep ineffective (#4417) ...

### What this PR does / why we need it?
The expert mapping table and weights of the dynamic EPLB were not
updated, causing the accuracy to be correct but not effective. This bug
has now been fixed.

- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2

---------

Signed-off-by: shenchuxiaofugui <1311027364@qq.com>

2025-11-29 15:18:29 +08:00

..

fused_moe

[bugfix] dep ineffective (#4417)

2025-11-29 15:18:29 +08:00

triton

【OPS】qwen3-next support triton chunk_gated_delta_rule ops (#4070)

2025-11-28 20:55:43 +08:00

__init__.py

[Refactor] [MoE] Rename moe-related classes & files (#3646)

2025-10-25 11:22:03 +08:00

activation.py

[refact] unified soc_version code (#4359)

2025-11-26 14:28:55 +08:00

attention.py

remove useless code (#3685)

2025-10-24 16:29:08 +08:00

expert_load_balancer.py

eplb redundant expert bugfix (#4291)

2025-11-21 14:24:35 +08:00

layernorm.py

[refact] unified soc_version code (#4359)

2025-11-26 14:28:55 +08:00

linear_op.py

[Feat] flashcomm_v2 optim solution (#3232)

2025-11-10 11:01:45 +08:00

linear.py

[Feat][BugFix]Support the Qwen3-Next-80B-A3B-Instruct quantization model&Fix the NZ issue (#4245)

2025-11-21 10:42:56 +08:00

register_custom_ops.py

Drop 0.11.0 support (#4377)

2025-11-24 17:08:20 +08:00

rotary_embedding.py

[refact] unified soc_version code (#4359)

2025-11-26 14:28:55 +08:00

vocab_parallel_embedding.py

[Bugfix] Fix MTP support for lmhead_tensor_parallel_size (#3915)

2025-10-31 10:30:28 +08:00

weight_prefetch.py

Update torch-npu version to 2.7.1 (#3896)

2025-10-31 17:16:31 +08:00