vLLM/vllm at e7900156e130c9880eb03b7c1f2df32820e7a2be - vLLM

assets

Add pydocstyle to the ruff rules (#52136 )

2026-09-16 16:44:29 +00:00

benchmarks

[Benchmark] Record model_id in bench latency/throughput --output-json (#58112 )

2026-09-25 16:43:37 +00:00

compilation

[Core] Model console logging as CLI configuration (#57205 )

2026-09-25 11:36:59 +01:00

config

[Bugfix] Disable sequence parallelism / async TP under batch invariance and add a TP regression test (#56377 )

2026-09-26 22:19:08 -04:00

cute_utils

[Kernel][DSV4.1] Fuse MXFP8 wo_b GEMM with sequence-parallel reduce-scatter (#57428 )

2026-09-22 01:07:17 -07:00

device_allocator

[Bugfix] Don't drop the rest of the allocator config when toggling expandable segments (#57982 )

2026-09-25 17:34:19 -05:00

distributed

[Bugfix][NIXL] Release a dead peer's NIXL state without waiting for TTL (#50047 )

2026-09-26 20:30:09 -07:00

engine

[Core] Model console logging as CLI configuration (#57205 )

2026-09-25 11:36:59 +01:00

entrypoints

[Fast Start] Add /health endpoint for the weight cache daemon (#58552 )

2026-09-27 17:48:54 +00:00

inputs

[Deprecation] Remove assistant_token_mask support (#57520 )

2026-09-19 00:17:51 +08:00

ir

Add pydocstyle to the ruff rules (#52136 )

2026-09-16 16:44:29 +00:00

kernels

[Refactor] Move auxiliary files out of the repository root (#58572 )

2026-09-24 12:38:56 -07:00

logging_utils

[Core][Logging] Fix JSON logging process decoration (#57957 )

2026-09-25 10:12:28 -06:00

lora

[Chore] Use Transformers v5 names and drop redundant processor use_fast (#58550 )

2026-09-24 14:14:10 +00:00

model_executor

[ROCm][Kimi-K3] Make VLLM_ROCM_USE_AITER_MOE_SITUV2 select a4w4/a8w4/a16w4 (#58201 )

2026-09-27 02:26:49 +00:00

models

[ROCm][Perf] Enable layer-aware CSA2 multi-stream overlap for DeepSeek-V4.1-Flash (#57407 )

2026-09-27 23:48:01 +08:00

multimodal

[Chore] Use Transformers v5 names and drop redundant processor use_fast (#58550 )

2026-09-24 14:14:10 +00:00

parser

[Bugfix] Support repsonse_format + tool_choice=auto (#56086 )

2026-09-27 21:17:34 +04:00

platforms

[Core] Model console logging as CLI configuration (#57205 )

2026-09-25 11:36:59 +01:00

plugins

Add pydocstyle to the ruff rules (#52136 )

2026-09-16 16:44:29 +00:00

profiler

[Profiler] Unify platform-aware torch profiling (#57460 )

2026-09-20 19:17:23 -07:00

ray

Add pydocstyle to the ruff rules (#52136 )

2026-09-16 16:44:29 +00:00

reasoning

[Bugfix][Reasoning] Count Kimi K3 reasoning tokens (#58372 )

2026-09-25 23:29:56 +00:00

renderers

[Security] Gate per-request multimodal processor kwargs (#58830 )

2026-09-26 11:10:35 +00:00

snapshot

[Frontend] Add reusable TP1 initialized-engine snapshots (#51360 )

2026-09-21 23:18:49 +00:00

third_party

Add pydocstyle to the ruff rules (#52136 )

2026-09-16 16:44:29 +00:00

tilelang_utils

[Bugfix][ROCm][GLM-5.3-Flash] Apply deferred tilelang.jit already on attribute access (#57192 )

2026-09-17 12:02:39 +00:00

tokenizers

[Bugfix][Frontend][Rust Frontend] Update DeepSeek V4.1 Flash reasoning effort mappings (#58316 )

2026-09-26 02:18:58 +00:00

tool_parsers

[Bugfix] Support repsonse_format + tool_choice=auto (#56086 )

2026-09-27 21:17:34 +04:00

tracing

Add pydocstyle to the ruff rules (#52136 )

2026-09-16 16:44:29 +00:00

transformers_utils

[Spec Decode] Enable Gemma4 DSpark adaptive verification with FlashInfer (#57263 )

2026-09-26 17:01:17 +08:00

triton_utils

[Feature] Triton kernel dispatcher (#43048 )

2026-09-25 04:07:43 +00:00

usage

[Bugfix] Close usage telemetry HTTP sessions (#51219 )

2026-08-08 00:29:36 +00:00

utils

[ROCm][Perf] Enable layer-aware CSA2 multi-stream overlap for DeepSeek-V4.1-Flash (#57407 )

2026-09-27 23:48:01 +08:00

v1

[Perf][Pooling] Avoid blocking seq_lens GPU-to-CPU copy for pooling in FlashInfer metadata builder (#57214 )

2026-09-27 16:06:38 +00:00

vllm_flash_attn

[Kernel] Resubmit PR 48666 - Gemma4 FP8 KV FA4 head dim 512 backend selection (#53175 )

2026-09-23 20:29:06 -07:00

__init__.py

Add pydocstyle to the ruff rules (#52136 )

2026-09-16 16:44:29 +00:00

_aiter_ops.py

[ROCm][Kimi-K3] Make VLLM_ROCM_USE_AITER_MOE_SITUV2 select a4w4/a8w4/a16w4 (#58201 )

2026-09-27 02:26:49 +00:00

_custom_ops.py

[Perf][Distributed] Add low-SM multimem reduce-scatter for SM100/SM103 (#55072 )

2026-09-25 03:27:21 +00:00

_xpu_ops.py

[XPU] Wire up SYCL apply_rotary_emb kernel in ApplyRotaryEmb (#55721 )

2026-09-22 20:43:24 -07:00

collect_env.py

[XPU] fix collecting oneccl version info (#47104 )

2026-08-04 11:53:28 +00:00

connections.py

Reject oversized media before fully downloading it (#51896 )

2026-08-24 01:15:09 +00:00

env_override.py

[Bugfix] Backport Inductor custom-op pattern matching fix (#58189 )

2026-09-22 14:26:49 -07:00

envs.py

[ROCm][Kimi-K3] Make VLLM_ROCM_USE_AITER_MOE_SITUV2 select a4w4/a8w4/a16w4 (#58201 )

2026-09-27 02:26:49 +00:00

exceptions.py

Add pydocstyle to the ruff rules (#52136 )

2026-09-16 16:44:29 +00:00

forward_context.py

[PCP] Support prefill context parallelism with data parallelism (#57075 )

2026-09-23 22:32:36 -04:00

logger.py

[Core][Logging] Fix JSON logging process decoration (#57957 )

2026-09-25 10:12:28 -06:00

logits_process.py

[Refactor] Remove dead code multiple places (#58002 )

2026-09-22 16:36:03 -04:00

logprobs.py

Add pydocstyle to the ruff rules (#52136 )

2026-09-16 16:44:29 +00:00

model_inspection.py

…

outputs.py

[AuxOutput] Add block-keyed storage for routed-expert outputs (#45635 )

2026-09-21 10:25:05 +00:00

pooling_params.py

Add pydocstyle to the ruff rules (#52136 )

2026-09-16 16:44:29 +00:00

py.typed

…

sampling_params.py

[Structured Outputs] Parse Lark grammars natively in the xgrammar backend (#58321 )

2026-09-25 04:35:10 +00:00

scalar_type.py

[Quantization] Enable humming wNaM asymmetric quant (zero_point) with compressed-tensors (#46528 )

2026-09-23 10:23:11 -04:00

scripts.py

…

sequence.py

…

tasks.py

[Frontend] Move api_server.py out openai folder (#52131 )

2026-08-19 09:43:46 +00:00

version.py

…