vllm/vllm at cfdf6b5024da02ab07431de9f7a0dbade264e7cc - vllm

assets

[Frontend] Remove librosa from audio dependency (#37058 )

2026-03-21 11:36:15 +08:00

benchmarks

[Bugfix] Add missing ASRDataset import and CLI args in benchmarks/throughput.py (#38114 )

2026-04-08 13:53:53 +00:00

compilation

fused qknorm+rope kernel optimization for SM9.0 (#37376 )

2026-04-12 19:58:37 -07:00

config

Update default load format in LoadConfig

2026-04-13 15:58:22 -04:00

device_allocator

[CI] Fix mypy for vllm/device allocator (#35518 )

2026-03-02 15:53:18 +00:00

distributed

fix(lmcache): correct store for cached requests and num_scheduled_tokens in lmcache_mp_connector.py (#39655 )

2026-04-13 03:29:19 +00:00

engine

[Feature] Add auto-detection for reasoning_config when only reasoning_parser is set (#38214 )

2026-04-10 01:36:26 +00:00

entrypoints

[Bugfix] stream failure when model name not in audio endpoints (#36679 )

2026-04-13 14:20:07 +00:00

inputs

[Misc] Reorganize inputs (#35182 )

2026-03-25 10:22:54 -07:00

ir

[vLLM IR] rework gemma_rms_norm (#39014 )

2026-04-07 01:37:00 -07:00

kernels

[vLLM IR] rework gemma_rms_norm (#39014 )

2026-04-07 01:37:00 -07:00

logging_utils

[vLLM IR] 1/N Implement IR skeleton and rms_norm op (#33825 )

2026-03-31 22:15:05 -04:00

lora

[LoRA] Support dual CUDA streams-Linear Layer (#35721 )

2026-04-13 10:57:07 +08:00

model_executor

[Bugfix] Reject non-nvfp4 dtypes when using the flashinfer_nvlink_one_sided all2all backend (#39717 )

2026-04-13 19:13:51 +00:00

multimodal

[Multimodal] Fix nested_tensors_equal: add length check for lists and tuple support (#38388 )

2026-04-09 04:40:37 +00:00

parser

[Tool] adjust_request to reasoning parser, and Gemma4 fixes (#39027 )

2026-04-08 19:04:04 +00:00

platforms

[Bugfix] Use is_integrated to detect UMA GPUs for memory reporting (#35356 )

2026-04-13 11:07:40 -07:00

plugins

[Frontend][4/n] Improve pooling entrypoints | pooling. (#39153 )

2026-04-09 10:09:45 +00:00

profiler

[BugFix][CPU] Add CPU profiler summary file output (#38366 )

2026-04-10 13:41:15 +08:00

ray

[Ray] Propagate third-party env vars to Ray workers via prefix matching (#34383 )

2026-02-17 01:08:42 -08:00

reasoning

[Feature] Add auto-detection for reasoning_config when only reasoning_parser is set (#38214 )

2026-04-10 01:36:26 +00:00

renderers

[Bugfix] Use dedicated MM processor cache in /tokenize to prevent sender-cache pollution (#38545 )

2026-04-01 21:14:49 -07:00

third_party

[FlashMLA] Update FlashMLA to expose new arguments (#32810 )

2026-01-21 22:02:39 -07:00

tokenizers

[Mistral Grammar] Support Grammar Factory (#38150 )

2026-04-06 10:28:51 -04:00

tool_parsers

[Bugfix] Fix GLM tool parser streaming with MTP or stream interval (#39253 )

2026-04-13 05:10:30 +00:00

tracing

[Feature] OTEL tracing during loading (#31162 )

2026-02-05 16:59:28 -08:00

transformers_utils

[model] support FireRedLID (#39290 )

2026-04-10 08:43:58 +00:00

triton_utils

Add XPU MLA Sparse backend for DeepSeek v3.2 (#33230 )

2026-03-11 19:19:15 +08:00

usage

replace cuda_device_count_stateless() to current_platform.device_count() (#37841 )

2026-03-31 22:32:54 +08:00

utils

[Bugfix] Use is_integrated to detect UMA GPUs for memory reporting (#35356 )

2026-04-13 11:07:40 -07:00

v1

[Bug] Fix rocm sparse attn indexer issue (#39225 )

2026-04-13 07:53:45 -07:00

vllm_flash_attn

[Attention] relax the head dim 512 and paged kv for sm90+FA4 (#38835 )

2026-04-08 18:23:18 +00:00

__init__.py

Remove bc-lint (#35274 )

2026-02-26 03:01:01 -08:00

_aiter_ops.py

[ROCm] Fix AITER ops fake impl and minor bugs (#36092 )

2026-04-09 17:56:17 -07:00

_custom_ops.py

fused qknorm+rope kernel optimization for SM9.0 (#37376 )

2026-04-12 19:58:37 -07:00

_oink_ops.py

[Perf] Add opt-in SM100 Oink RMSNorm custom-op path (#31828 )

2026-02-24 23:01:53 -08:00

_xpu_ops.py

Support FP8 KVCache on XPU (#37731 )

2026-04-12 03:53:32 +00:00

beam_search.py

[Misc] Reorganize inputs (#35182 )

2026-03-25 10:22:54 -07:00

collect_env.py

[XPU]Enhance environment collection for Intel XPU and optimize layout (#35698 )

2026-04-13 12:51:46 +08:00

connections.py

[CI] Add retry with 4x backoff to HTTP fetches for transient failures (#37218 )

2026-03-19 19:00:20 +00:00

env_override.py

[ZenCPU] Make PT Backport Patch Accessible to vLLM (#38205 )

2026-04-10 08:29:35 +00:00

envs.py

[compile] Enable AOT compile with batch invariance mode. (#39201 )

2026-04-12 19:58:33 -07:00

exceptions.py

[openapi server] log exception in exception handler(2/N) (#36201 )

2026-03-10 20:16:30 -07:00

forward_context.py

[vLLM IR] 1/N Implement IR skeleton and rms_norm op (#33825 )

2026-03-31 22:15:05 -04:00

logger.py

[Log] Log once in local node by default (#37568 )

2026-03-19 12:04:59 -07:00

logits_process.py

[Misc] Refactor tokenizer interface (#29693 )

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

logprobs.py

Make mypy opt-out instead of opt-in (#33205 )

2026-01-29 09:12:26 +00:00

model_inspection.py

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

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

outputs.py

[V0 Deprecation] Remove unused MM placeholders in request output (#34944 )

2026-02-20 06:19:23 -08:00

pooling_params.py

[Model] Deprecate the score task (this will not affect users). (#37537 )

2026-03-20 08:07:56 +00:00

py.typed

…

sampling_params.py

[Mistral Grammar] Support Grammar Factory (#38150 )

2026-04-06 10:28:51 -04:00

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

[Model Runner V2][Minor] Simplify PP logic (#38031 )

2026-03-24 13:57:17 -07:00

tasks.py

[Model] Deprecate the score task (this will not affect users). (#37537 )

2026-03-20 08:07:56 +00:00

version.py

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

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