Chenheli Hua 48eb8eba58 [Temp fix] Disable torch.compile for Qwen2.5 VL's VisionBlock temporarily. (#27760) ...

Signed-off-by: Chenheli Hua <huachenheli@outlook.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>

2025-10-29 23:17:48 +00:00

..

assets

[VLM] Add Qwen3-VL generation test (#25185)

2025-10-29 12:19:37 +00:00

attention

[Misc][qwen2_5_vl][torch.compile] Enable supports_torch_compile on generic nn.Module and demonstrate speedup on Qwen Vision model (#23207)

2025-10-28 22:36:43 +00:00

benchmarks

[Frontend] Add vllm bench sweep to CLI (#27639)

2025-10-29 05:59:48 -07:00

compilation

[Misc][qwen2_5_vl][torch.compile] Enable supports_torch_compile on generic nn.Module and demonstrate speedup on Qwen Vision model (#23207)

2025-10-28 22:36:43 +00:00

config

[CI/Build] Move pre-commit only scripts to tools/pre_commit (#27657)

2025-10-29 08:04:33 +00:00

device_allocator

[Chore] Separate out vllm.utils.platform_utils.py (#27374)

2025-10-23 19:08:06 +00:00

distributed

[BugFix] Fix handling of resumed reqs in SharedStorageConnector (#27719)

2025-10-29 20:16:52 +00:00

engine

[chore] Remove models weight on S3 logic (#27725)

2025-10-29 10:29:49 +00:00

entrypoints

[Frontend] Add vllm bench sweep to CLI (#27639)

2025-10-29 05:59:48 -07:00

inputs

[Misc] Move utils to avoid conflicts with stdlib, and move tests (#27169)

2025-10-19 05:20:55 -07:00

logging_utils

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

lora

[Kernel] Enable moe LoRA kernel support FP16 (#27468)

2025-10-27 19:48:37 +08:00

model_executor

[Temp fix] Disable torch.compile for Qwen2.5 VL's VisionBlock temporarily. (#27760)

2025-10-29 23:17:48 +00:00

multimodal

[Misc] Raise error for missing video metadata in MultiModalDataParser (#27664)

2025-10-29 10:06:42 +00:00

platforms

[Bug] Raise error explicitly if using incompatible backend (#27424)

2025-10-29 13:29:20 -04:00

plugins

[Frontend][4/N] Improve all pooling task | Add plugin pooling task (#26973)

2025-10-23 14:46:18 +00:00

profiler

[Frontend] Add vllm bench sweep to CLI (#27639)

2025-10-29 05:59:48 -07:00

ray

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

reasoning

[Model][MiniMax-M2] Support MiniMax-M2 Model (#27535)

2025-10-27 00:59:11 +08:00

third_party

fix some typos (#24071)

2025-09-02 20:44:50 -07:00

transformers_utils

[Bugfix][CI] Fix config resolving logic with remote models (#27610)

2025-10-28 00:48:32 +00:00

triton_utils

[Misc] Update TritonLanguagePlaceholder to have attributes that are used by Flash Linear Attention ops. (#26853)

2025-10-15 08:37:49 +00:00

usage

[Misc] Add TPU usage report when using tpu_inference. (#27423)

2025-10-23 20:29:37 -07:00

utils

[Misc] Make LayerBlockType a Literal instead of Enum (#27658)

2025-10-28 16:23:35 +00:00

v1

[Bug] Fix DBO IMA issue for DeepEPHT (#27666)

2025-10-29 16:28:27 -04:00

vllm_flash_attn

[BugFix] Fix vllm_flash_attn install issues (#17267)

2025-04-27 17:27:56 -07:00

__init__.py

[V0 Deprecation] Remove V0 executors (#27142)

2025-10-21 11:09:37 -07:00

_bc_linter.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

_custom_ops.py

[Kernel] Add GPTQv2 format support for low-bit or asymmetric quantization, by adapting gptq_gemm (#26092)

2025-10-23 23:26:13 -04:00

_ipex_ops.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

beam_search.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

collect_env.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

connections.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

env_override.py

[BugFix] fix graph partition signature (#27139)

2025-10-18 17:34:36 -04:00

envs.py

use_aot_compile should respect VLLM_DISABLE_COMPILE_CACHE (#27698)

2025-10-29 17:08:54 +00:00

forward_context.py

[LoRA] LoRA cuda graph specialization (#25914)

2025-10-20 04:21:09 +00:00

logger.py

[Log] Optimize Startup Log (#26740)

2025-10-24 19:27:04 -04:00

logits_process.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

logprobs.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

outputs.py

[Model] Add num_cached_tokens for PoolingRequestOutput (#27378)

2025-10-23 14:03:42 +08:00

pooling_params.py

[Frontend][4/N] Improve all pooling task | Add plugin pooling task (#26973)

2025-10-23 14:46:18 +00:00

py.typed

Add py.typed so consumers of vLLM can get type checking (#1509)

2023-10-30 14:50:47 -07:00

sampling_params.py

[GPT-OSS] Structure_Tag support for gpt-oss tool-call in cot (#25515)

2025-10-17 21:55:54 -07:00

scalar_type.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

scripts.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

sequence.py

[V0 Deprecation] Remove V0 executors (#27142)

2025-10-21 11:09:37 -07:00

tasks.py

[Frontend][4/N] Improve all pooling task | Add plugin pooling task (#26973)

2025-10-23 14:46:18 +00:00

tracing.py

[Misc] Move utils to avoid conflicts with stdlib, and move tests (#27169)

2025-10-19 05:20:55 -07:00

version.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00