tanhaoan333 f8315f5717 [bugfix]Qwen2.5VL accurate question (#6975) ...

### What this PR does / why we need it?
The attention mechanism in the ViT model architecture of Qwen2.5VL
consists of two parts and does not support using cache to pass sequence
lengths.
### Does this PR introduce _any_ user-facing change?
remove seq_lens_cache
### How was this patch tested?

- vLLM version: v0.16.0
- vLLM main:
15d76f74e2

---------

Signed-off-by: tanhaoan333 <tanhaoan@huawei.com>

2026-03-04 22:02:29 +08:00

..

_310p

[300I][Bugfix] fix unquant model weight nd2nz error (#6851)

2026-03-03 15:57:26 +08:00

_cann_ops_custom

[Kernel] add custom op GmmSwigluQuantWeightNzTensorList (#3804)

2025-11-28 18:06:39 +08:00

attention

[feat]ds3.2 pcp support mtp and chunkprefill (#6917)

2026-03-03 19:03:50 +08:00

compilation

[Triton][Config] Add muls_add triton kernel and refactor AscendCompilationConfig (#5518)

2026-03-02 17:54:25 +08:00

core

[P/D][v0.16.0]Adapt to RecomputeScheduler in vLLM 0.16.0 (#6898)

2026-03-02 23:24:03 +08:00

device

[misc] move mxfp_compat into device to decouple from quantization init chain (#6918)

2026-03-02 18:17:01 +08:00

device_allocator

[Lint]Style: Convert vllm-ascend/ to ruff format(Batch #2) (#5977)

2026-01-19 08:59:46 +08:00

distributed

[BugFix][PCP] Fix presion bugs for pcp/dcp in PD disaggregate (#6876)

2026-03-02 16:11:00 +08:00

eplb

[EPLB] Reduce the memory used for heat aggregation (#6729)

2026-02-24 18:02:24 +08:00

kv_offload

[Main2Main] Upgrade vLLM to 0226 (#6813)

2026-02-27 16:05:21 +08:00

lora

[Lint]Style: Convert vllm-ascend/ to ruff format(Batch #5) (#5996)

2026-01-24 22:45:38 +08:00

model_loader

[Lint]Style: Convert vllm-ascend/ to ruff format(Batch #6) (#6001)

2026-01-24 22:08:33 +08:00

ops

[bugfix]Qwen2.5VL accurate question (#6975)

2026-03-04 22:02:29 +08:00

patch

[Bugfix] Fix the acceptance rates dorp issue when applying eagle3 to QuaRot model (#6914)

2026-03-04 11:29:49 +08:00

quantization

[Model]Add Qwen3-Omni quantization Ascend NPU adaptation and optimization (#6828)

2026-03-03 00:07:23 +08:00

sample

clean 0.15.0 support (#6852)

2026-02-28 09:20:57 +08:00

spec_decode

[Ops][BugFix] Fix RoPE shape mismatch for mtp models with flashcomm v1 enabled (#6939)

2026-03-04 16:02:08 +08:00

worker

[Bugfix] Fix the acceptance rates dorp issue when applying eagle3 to QuaRot model (#6914)

2026-03-04 11:29:49 +08:00

xlite

[Lint]Style: Convert vllm-ascend/ to ruff format(Batch #10) (#6173)

2026-02-06 15:35:06 +08:00

__init__.py

[Lint]Style: Convert vllm-ascend/compilation to ruff format (#5912)

2026-01-16 20:57:46 +08:00

ascend_config.py

[Triton][Config] Add muls_add triton kernel and refactor AscendCompilationConfig (#5518)

2026-03-02 17:54:25 +08:00

ascend_forward_context.py

add mxfp8 moe quantization (#6670)

2026-03-02 11:04:06 +08:00

batch_invariant.py

implement batch invariant with ascendc (#6590)

2026-02-10 14:15:26 +08:00

cpu_binding.py

[CPU binding] Implement global CPU slicing and improve IRQ binding for Ascend NPUs (#6945)

2026-03-03 17:20:52 +08:00

envs.py

[MISC] Clean up useless env USE_OPTIMIZED_MODEL (#6618)

2026-02-09 15:38:58 +08:00

flash_common3_context.py

[Lint]Style: Convert vllm-ascend/compilation to ruff format (#5912)

2026-01-16 20:57:46 +08:00

meta_registration.py

[Ops][Refactor] Remove custom rotary_embedding operator (#6523)

2026-02-07 09:24:05 +08:00

platform.py

[Triton][Config] Add muls_add triton kernel and refactor AscendCompilationConfig (#5518)

2026-03-02 17:54:25 +08:00

profiling_config.py

[Core][Misc] Clean up ProfileExecuteDuration (#6461)

2026-02-01 20:06:01 +08:00

utils.py

[BugFix] Improve GDN layer detection for multimodal models (#6941)

2026-03-03 20:08:39 +08:00