LookAround0301 5ec96fd46c [long_seq_Feat] support chunk prefill (#4158) ...

### What this PR does / why we need it?
1、qwen GQA attention_v1 optim
2、DeepSeek MLA refactor, all gather q -> all gather kv 
3、modelrunner refactor for chunk prefill, we remove some code not use

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

---------

Signed-off-by: LookAround <lixushi@huawei.com>
Signed-off-by: Delphine-Nic <tanwenqin@huawei.com>
Co-authored-by: Delphine-Nic <tanwenqin@huawei.com>

2025-11-14 08:43:37 +08:00

..

attention

[long_seq_Feat] support chunk prefill (#4158)

2025-11-14 08:43:37 +08:00

compilation

[Test]Add unit test for compilation/acl_graph.py (#3039)

2025-09-19 21:31:17 +08:00

core

Upgrade to new vllm commit (#3719)

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

device_allocator

add ut for device allocator/camem and mutistream/layers (#2037)

2025-07-31 19:17:27 +08:00

distributed

[Feat] flashcomm_v2 optim solution (#3232)

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

eplb

[CI]Add EPLB CI. (#3568)

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

fake_weight

[CI] Add unit test framework (#1201)

2025-06-16 18:32:28 +08:00

kv_connector

[feature] support pcp + mtp (in pd co-locate scenario) (#4098)

2025-11-12 17:22:21 +08:00

model_loader/netloader

Upgrade to new vllm commit (#3719)

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

models

[BugFix] Fixes Qwen3-Next enable nz accuracy problem (#4058)

2025-11-10 20:54:57 +08:00

ops

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

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

patch/worker/patch_common

[Refactor] refactor patch module (#3555)

2025-10-21 20:19:46 +08:00

quantization

[BugFix] Fixes Qwen3-Next enable nz accuracy problem (#4058)

2025-11-10 20:54:57 +08:00

sample

[UT] Fix test_sample_recovered_tokens_pytorch_autoregressive (#3434)

2025-10-24 11:20:57 +08:00

torchair

[Test]Add ut test qwen3_moe and sfa (#4121)

2025-11-13 16:09:22 +08:00

worker

Upgrade to 0.11.1 newest vllm commit (#3982)

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

__init__.py

[2/4][Refactor] Refactor torchair utils (#1892)

2025-07-21 19:43:30 +08:00

base.py

[Feature]: implement the fusion of allreduce and matmul in prefill phase when tp is enabled (#1926)

2025-07-28 15:13:37 +08:00

conftest.py

[1/N][CustomOp] Register activation customop instead of overwrite forward_oot (#1841)

2025-07-18 23:07:14 +08:00

test_ascend_config.py

oproj TP support acl graph (#4073)

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

test_envs.py

[Misc] Remove redundant imported envs, using envs_ascend instead (#2193)

2025-08-14 09:33:39 +08:00

test_platform.py

[Core] Restore scheduling logic under default configuration (#3967)

2025-11-10 17:48:56 +08:00

test_utils.py

[BugFix] Fixes Qwen3-Next enable nz accuracy problem (#4058)

2025-11-10 20:54:57 +08:00