Ruri dd7a25063c [Feat] Prefetching Attention QKV Linear Weight With AddRmsNormQuant Custom Op (#3517) ...

### What this PR does / why we need it?

- `qkv_proj.weight` prefetching has been implemented with `Quant` op,
when `AddRmsNormQuant` is enabled (#3465) `qkv_proj.weight` prefetching
won't work
- Implement `qkv_proj.weight` prefetching with `AddRmsNormQuant`

### Does this PR introduce _any_ user-facing change?

None.

### How was this patch tested?

Tested on `Qwen3-235B-A22B-W8A8`
<img width="1868" height="109" alt="image"
src="https://github.com/user-attachments/assets/0bc28082-0287-4d5c-b8f6-f907c3134d36"
/>


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

---------

Signed-off-by: zhoux77899 <zhouxiang100@huawei.com>

2025-10-23 10:07:37 +08:00

..

moe

Reapply "[MoE] [Refactor] Remove manual memory cleanup (#3365)" (#3483) (#3512)

2025-10-22 11:41:30 +08:00

__init__.py

[MoE] [Refactor] Combine common_fused_moe and fused_moe (#3176)

2025-10-09 14:12:46 +08:00

activation.py

[main] mlp weight prefetch in Qwen Dense Models (#2816)

2025-09-11 21:20:09 +08:00

attention.py

Disaggregate prefill for kv cache register style (#950)

2025-07-26 17:15:47 +08:00

casual_conv1d.py

[2/N][Refactor][Qwen3-Next] remove redundant methods and patch methods in Qwen3NextGatedDeltaNet (#3082)

2025-09-24 11:25:42 +08:00

common_fused_moe.py

Reapply "[MoE] [Refactor] Remove manual memory cleanup (#3365)" (#3483) (#3512)

2025-10-22 11:41:30 +08:00

expert_load_balancer.py

Add static EPLB (#1116)

2025-06-09 19:28:11 +08:00

fla.py

[BugFix][mian] Fixed a triton kernel bug of layer_norm_fwd_kernel for Qwen3-next (#3549)

2025-10-21 20:20:57 +08:00

layernorm.py

[Feat] Prefetching Attention QKV Linear Weight With AddRmsNormQuant Custom Op (#3517)

2025-10-23 10:07:37 +08:00

linear_op.py

[Feat] Flash comm allgher ep (#3334)

2025-10-15 19:36:32 +08:00

linear.py

[feat][torchair] support super kernel feat for quantized dsr1 (#3485)

2025-10-20 20:04:37 +08:00

register_custom_ops.py

Revert "[Feat] Shared expert dp for deepseek and deepseek_mtp (#3495)" (#3586)

2025-10-21 22:24:30 +08:00

rotary_embedding.py

Revert "Add mrope op fusion (#3509)" (#3562)

2025-10-20 20:19:24 +08:00

sigmoid_gating.py

[2/N][Refactor][Qwen3-Next] remove redundant methods and patch methods in Qwen3NextGatedDeltaNet (#3082)

2025-09-24 11:25:42 +08:00

vocab_parallel_embedding.py

[Feature] optimize sp & qwen3 next support sp. (#3225)

2025-10-13 23:02:12 +08:00

weight_prefetch.py

[Feat]Qwen3 Moe supports npu_add_rms_norm_quant op by default, update op with bias, resolve conflict with weight prefetch (#3465)

2025-10-17 09:30:51 +08:00