vllm/vllm at 4ca62a0dbdba8b8aaf40438c99d20cdb56db8d5d - vllm

assets

[Model] Nemotron Parse 1.1 Support (#30864 )

2026-01-05 13:00:14 -08:00

attention

[Model] Support Step1 Model (#32511 )

2026-01-18 10:20:46 +00:00

benchmarks

feat: spec decode with draft models (#24322 )

2026-01-19 16:05:46 -05:00

compilation

[Core] Whisper support torch.compile (#30385 )

2026-01-19 10:02:31 +00:00

config

[Model] Use context managers for encoder- and LM-only mode (#32605 )

2026-01-20 11:43:38 +08:00

device_allocator

refactor: find_loaded_library (#31866 )

2026-01-07 06:42:20 +00:00

distributed

[XPU]Support AgRsAll2AllManager on XPU device (#32654 )

2026-01-20 14:27:24 +00:00

engine

[Model] Use context managers for encoder- and LM-only mode (#32605 )

2026-01-20 11:43:38 +08:00

entrypoints

[Feat] allow inplace loading lora (#31326 )

2026-01-20 10:15:20 +08:00

grpc

[grpc] Support gRPC server entrypoint (#30190 )

2026-01-07 23:24:46 -08:00

inputs

Add Multimodal Processor Benchmark (#29105 )

2026-01-01 19:26:53 -08:00

logging_utils

[4/N][Attention] Move MLA common to model_executor (#32060 )

2026-01-13 09:08:45 -08:00

lora

[Feat] allow inplace loading lora (#31326 )

2026-01-20 10:15:20 +08:00

model_executor

[PluggableLayer][1/N] Define PluggableLayer (#32331 )

2026-01-20 16:19:21 +00:00

multimodal

[Core] Cleanup shm based object store on engine shutdown (#32429 )

2026-01-20 08:53:37 +00:00

platforms

[Attention][MLA] Make FLASHINFER_MLA the default MLA backend on Blackwell, and TRTLLM the default prefill (#32615 )

2026-01-19 18:41:34 -05:00

plugins

[Frontend] Resettle pooling entrypoints (#29634 )

2025-12-01 15:30:43 +08:00

profiler

[Logs] Optimize startup logs 4 (#29903 )

2025-12-13 16:12:53 -05:00

ray

[Small] Capture AttributeError when checking ray dependency. (#29024 )

2025-11-20 22:54:10 -08:00

reasoning

[Refactor] [11/N] to simplify the mcp architecture (#32396 )

2026-01-15 18:49:31 +08:00

third_party

fix some typos (#24071 )

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

tokenizers

[Refactor] [6/N] to simplify the vLLM openai chat_completion serving architecture (#32240 )

2026-01-13 13:01:39 +00:00

tool_parsers

[bugfix] Fix online serving crash when text type response_format is received (#26822 )

2026-01-16 12:23:54 +08:00

transformers_utils

[Bugfix] Replace PoolingParams.normalize with use_activation (#32243 )

2026-01-13 10:45:42 +00:00

triton_utils

[mypy] Enable type checking for more directories (#29674 )

2025-11-28 08:39:27 -08:00

usage

[Refactor][TPU] Remove torch_xla path and use tpu-inference (#30808 )

2026-01-07 16:07:16 +08:00

utils

[Bugfix] Fix the fp8_mqa_logits dim mismatch (#32652 )

2026-01-20 18:48:07 +08:00

v1

[Metrics] Complete removal of deprecated vllm:time_per_output_token_seconds metric (#32661 )

2026-01-20 12:28:41 +00:00

vllm_flash_attn

…

__init__.py

[V0 Deprecation] Remove V0 executors (#27142 )

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

_aiter_ops.py

[Refactor] Make FP8 Linear Ops use kernel abstraction (#27814 )

2026-01-20 14:48:20 +08:00

_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

[Refactor] Remove unused cutlass moe problem size function (#32047 )

2026-01-18 12:46:59 -08:00

_ipex_ops.py

[Misc] Remove unused custom ops copy_blocks and copy_blocks_mla (#30967 )

2025-12-23 18:22:35 -08:00

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

[CI] Breakup h200 tests (#30499 )

2026-01-16 06:23:22 +00:00

envs.py

[Core] Cleanup shm based object store on engine shutdown (#32429 )

2026-01-20 08:53:37 +00:00

exceptions.py

[OpenAI] Extend VLLMValidationError to additional validation parameters (#31870 )

2026-01-07 14:45:49 +00:00

forward_context.py

[Core] Whisper support torch.compile (#30385 )

2026-01-19 10:02:31 +00:00

logger.py

Make the httpx logger less annoying when Transformers v5 is installed (#30480 )

2025-12-11 15:44:56 +00:00

logits_process.py

[Misc] Refactor tokenizer interface (#29693 )

2025-11-29 04:02:21 -08:00

logprobs.py

[Core] Switch Flat logprob control from environment variable to SamplingParams (#28914 )

2025-11-19 02:10:02 +00:00

model_inspection.py

[UX] Add vLLM model inspection view (#29450 )

2026-01-09 10:12:35 -07:00

outputs.py

[Feature] Support recording expert indices for rollout router replay (#28284 )

2026-01-12 06:23:04 -08:00

pooling_params.py

[Bugfix] Replace PoolingParams.normalize with use_activation (#32243 )

2026-01-13 10:45:42 +00:00

py.typed

…

sampling_params.py

[bugfix] Fix online serving crash when text type response_format is received (#26822 )

2026-01-16 12:23:54 +08:00

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

[Chore] Remove more V0 dead code from sequence.py (#31783 )

2026-01-06 10:25:14 +00:00

tasks.py

[Refactor] Separate sequence and token pooling types (#32026 )

2026-01-10 04:53:24 +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