shaopeng-666 3653f33878 avoid mrope fusion op when running qwen2.5-vl on a+x machine (#4270) ...

### What this PR does / why we need it?
avoid mrope fusion op when running qwen2.5-vl on a+x machine
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
Test text VQA accuracy on G8600 with aisbench

- vLLM version: v0.11.0
- vLLM main:
2918c1b49c

---------

Signed-off-by: 李少鹏 <lishaopeng21@huawei.com>

2025-11-19 22:31:14 +08:00

..

attention

[long seq feat]GQA support long-prefill-token-threshold and fixbug (#4209)

2025-11-19 18:10:27 +08:00

compilation

[Bugfix] fix hang in async scheduling (#4233)

2025-11-19 14:47:19 +08:00

core

Upgrade to 0.11.1 newest vllm commit (#3982)

2025-11-12 23:01:19 +08:00

device_allocator

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

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

distributed

[bugfix] fix proxy hen host ip using domain name (#4243)

2025-11-18 16:30:51 +08:00

eplb

[Bugfix] fix nightly multi-node EPLB tests' "DYNAMIC_EPLB=true" environment not working (#4223)

2025-11-19 21:31:58 +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 (#3982)

2025-11-12 23:01:19 +08:00

ops

avoid mrope fusion op when running qwen2.5-vl on a+x machine (#4270)

2025-11-19 22:31:14 +08:00

patch

[Bugfix] fix nightly multi-node EPLB tests' "DYNAMIC_EPLB=true" environment not working (#4223)

2025-11-19 21:31:58 +08:00

quantization

[Bugfix] fix mtp profile run error where main model and mtp model use different quantization (#4102)

2025-11-13 11:02:31 +08:00

sample

[Perf] Remove D2H operations to imporve performance (#4063)

2025-11-12 09:08:55 +08:00

spec_decode

Upgrade to 0.11.1 newest vllm commit (#3982)

2025-11-12 23:01:19 +08:00

torchair

remove get_metadata_cls (#4087)

2025-11-19 14:58:17 +08:00

worker

[long seq feat]GQA support long-prefill-token-threshold and fixbug (#4209)

2025-11-19 18:10:27 +08:00

__init__.py

[Misc][Doc] Add service profiling feature with user guide (#3756)

2025-11-12 09:07:14 +08:00

ascend_config.py

oproj TP support acl graph (#4073)

2025-11-11 19:39:06 +08:00

ascend_forward_context.py

[refactor]support gatingtopk operator generalization (#2958)

2025-11-19 10:38:56 +08:00

cpu_binding.py

[main] support cpu binding (#3546)

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

envs.py

[Bugfix] fix nightly multi-node EPLB tests' "DYNAMIC_EPLB=true" environment not working (#4223)

2025-11-19 21:31:58 +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

[main][misc]change default capture size for Qwen3-MoE when using full dp (#4199)

2025-11-18 08:41:45 +08:00

profiling_config.py

[Misc][Doc] Add service profiling feature with user guide (#3756)

2025-11-12 09:07:14 +08:00

utils.py

[main][misc]change default capture size for Qwen3-MoE when using full dp (#4199)

2025-11-18 08:41:45 +08:00