vllm/vllm at 9e19f8338b4098047175ca3119d5ae0368bcf24a - vllm

assets

[Model] Nemotron Parse 1.1 Support (#30864 )

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

benchmarks

[Bug] Fix pooling model benchmark script (#36300 )

2026-03-09 11:17:45 -04:00

compilation

[torch.compile] Use FakeTensors instead of real GPU tensors for single-size compilation (#36093 )

2026-03-11 16:07:09 +00:00

config

[Model Runner V2] Add probabilistic rejection sampling for spec decoding (#35461 )

2026-03-11 14:04:32 -07:00

device_allocator

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

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

distributed

[KV Connector] Support using FlexKV as KV Cache Offloading option. (#34328 )

2026-03-12 00:46:20 -07:00

engine

[Frontend][Core] Revert "Add shutdown timeout" (#34730 and #36270 ) (#36628 )

2026-03-10 06:20:41 -07:00

entrypoints

[Frontend] Split OpenAIServingModels into OpenAIModelRegistry + OpenAIServingModels (#36536 )

2026-03-12 03:29:37 -07:00

inputs

[Renderer] Move MM Hash parsing into Renderer (#34711 )

2026-02-17 19:18:55 -08:00

kernels

[Kernel][Helion][13/N] Force static_shapes=False in helion register (#36677 )

2026-03-12 05:35:29 +00:00

logging_utils

[Logging] add --disable-access-log-for-endpoints CLI option (#30011 )

2026-01-26 21:49:03 +00:00

lora

fix(lora): use replaced_module_name in pooling model name check (#36402 )

2026-03-11 03:11:27 -07:00

model_executor

[Perf] add packed recurrent fast path for decode (#36596 )

2026-03-12 04:01:57 -07:00

multimodal

[Doc] Fix duplicate words in comments (#36713 )

2026-03-10 21:28:31 -07:00

parser

[Misc] Remove duplicate parser registration (#36303 )

2026-03-07 09:37:01 -05:00

platforms

[Bugfix][ROCm] Strip block_size before attention backend validation (#36274 )

2026-03-11 13:37:31 -07:00

plugins

[Deprecation][1/2] Remove items deprecated in v0.18 (#36470 )

2026-03-09 03:43:23 -07:00

profiler

Add PyTorch profiler schedule support with warmup/active iterations (#35240 )

2026-03-04 12:53:38 -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

[NemotronH] Small fix reasoning parser (#36635 )

2026-03-11 02:44:41 -07:00

renderers

[Misc] Clean up renderers (#36770 )

2026-03-11 16:39:29 +00:00

third_party

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

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

tokenizers

[Misc] Clean up renderers (#36770 )

2026-03-11 16:39:29 +00:00

tool_parsers

[Bugfix] Fix minimax_m2 tool parser when stream interval > 1 (#35895 )

2026-03-12 10:25:14 +08:00

tracing

[Feature] OTEL tracing during loading (#31162 )

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

transformers_utils

[Misc] Clean up renderers (#36770 )

2026-03-11 16:39:29 +00:00

triton_utils

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

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

usage

[Deprecation] Remove deprecated environment variables (#32812 )

2026-01-22 02:25:16 +00:00

utils

[BugFix] Fix multiple/duplicate stdout prefixes (#36822 )

2026-03-12 12:23:21 +08:00

v1

[BugFix] Fix multiple/duplicate stdout prefixes (#36822 )

2026-03-12 12:23:21 +08:00

vllm_flash_attn

[Attention] FA4 integration (#32974 )

2026-03-01 23:44:57 +00:00

__init__.py

Remove bc-lint (#35274 )

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

_aiter_ops.py

[ROCm][Quantization] Add Composable Kernel (CK) backend support for M… (#34301 )

2026-02-28 03:37:01 +00:00

_custom_ops.py

[torch.compile] Add support for non-contiguous fused RMSNorm + group quant (#36551 )

2026-03-11 10:56:55 -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

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

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

beam_search.py

[Frontend] Add Support for MM Encoder/Decoder Beam Search (Offline) (#36153 )

2026-03-06 01:16:56 -08:00

collect_env.py

[Refactor] Remove unused dead code (#33718 )

2026-02-03 21:25:11 -08:00

connections.py

[Misc] Replace urllib's urlparse with urllib3's parse_url (#32746 )

2026-01-22 16:37:15 +08:00

env_override.py

[compile] Stop unconditionally patching constrain_to_fx_strides (#36152 )

2026-03-06 10:17:27 -05:00

envs.py

[Perf] add packed recurrent fast path for decode (#36596 )

2026-03-12 04:01:57 -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

[Bugfix][CI] fix typos (#34934 )

2026-03-05 17:05:46 +00:00

logger.py

[CI] Enable mypy coverage for individual excluded files (#34292 )

2026-02-16 07:34:29 -08:00

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

[Perf] Compute maxsim in worker side, reducing redundant copies, 2.7% E2E throughput improvement (#36159 )

2026-03-09 20:55:58 -07:00

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

[CI] Bump mypy version to 1.19.1 (#36104 )

2026-03-10 09:18:28 -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

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

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

tasks.py

[Model] Consolidate score logic by introduce score_type (#36479 )

2026-03-10 13:32:25 +00:00

version.py

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

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