ZYang6263 d08401d1e7 [Main][Bugfix]Avoid using the fusion operator in the MOE model (#3834) ...

### What this PR does / why we need it?
The current MatmulReduceScatter operator experiences performance
degradation in small-shape scenarios, so it determines whether to use
this operator by judging the size of the shape.

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

### How was this patch tested?

- vLLM version: v0.11.0rc3
- vLLM main:
https://github.com/vllm-project/vllm/commit/releases/v0.11.1

---------

Signed-off-by: ZYang6263 <zy626375@gmail.com>

2025-10-28 23:30:27 +08:00

..

attention

support prefill cache mode use fia op (#3696)

2025-10-27 19:41:07 +08:00

compilation

[feat]dcp pcp support aclgraph (#3731)

2025-10-27 09:58:23 +08:00

core

Upgrade to new vllm commit (#3719)

2025-10-25 15:36:32 +08:00

device_allocator

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

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

distributed

Upgrade to new vllm commit (#3719)

2025-10-25 15:36:32 +08:00

eplb

[CI]Add EPLB CI. (#3568)

2025-10-21 22:58:02 +08:00

kv_offload

Upgrade to 0.11.1 newest vllm commit (#3762)

2025-10-28 14:55:03 +08:00

lora

[1/N][Refactor] Refactor code to adapt with vllm main (#3612)

2025-10-24 16:55:08 +08:00

model_loader

Upgrade to new vllm commit (#3719)

2025-10-25 15:36:32 +08:00

models

Upgrade to 0.11.1 newest vllm commit (#3762)

2025-10-28 14:55:03 +08:00

ops

[Main][Bugfix]Avoid using the fusion operator in the MOE model (#3834)

2025-10-28 23:30:27 +08:00

patch

Upgrade to new vllm commit (#3719)

2025-10-25 15:36:32 +08:00

quantization

【Bugfix】bugfix for weight load of kimi-k2 (#3798)

2025-10-27 21:18:35 +08:00

sample

Upgrade to 0.11.1 newest vllm commit (#3762)

2025-10-28 14:55:03 +08:00

spec_decode

Upgrade to 0.11.1 newest vllm commit (#3762)

2025-10-28 14:55:03 +08:00

torchair

[main] remove dbo code (#3712)

2025-10-25 15:53:01 +08:00

worker

Upgrade to 0.11.1 newest vllm commit (#3762)

2025-10-28 14:55:03 +08:00

__init__.py

[1/N][Refactor] Refactor code to adapt with vllm main (#3612)

2025-10-24 16:55:08 +08:00

ascend_config.py

[1/N][Refactor] Refactor code to adapt with vllm main (#3612)

2025-10-24 16:55:08 +08:00

ascend_forward_context.py

[Main][Bugfix]Avoid using the fusion operator in the MOE model (#3834)

2025-10-28 23:30:27 +08:00

cpu_binding.py

[main] support cpu binding (#3546)

2025-10-21 09:17:03 +08:00

envs.py

[main] remove dbo code (#3712)

2025-10-25 15:53:01 +08:00

meta_registration.py

Fix the bugs about operator registration by PyTorch Dispatcher (#2786)

2025-09-13 11:58:52 +08:00

platform.py

Upgrade to 0.11.1 newest vllm commit (#3762)

2025-10-28 14:55:03 +08:00

utils.py

Upgrade to 0.11.1 newest vllm commit (#3762)

2025-10-28 14:55:03 +08:00