vLLM/vllm at 9bca7d840d7fa4677e58e7d163ddd191cccc40b7 - vLLM

assets

[Bugfix] Align OpenCV video metadata timeline (#47099 )

2026-06-30 20:43:42 +00:00

benchmarks

[MISC][Bench] refactor throughput and reuse serve's get samples (#50981 )

2026-08-06 10:31:23 +00:00

compilation

[ROCm] Fix AITER all-reduce fusion coverage (#50802 )

2026-08-06 14:52:23 +08:00

config

Interns2mobius support (#51149 )

2026-08-06 10:39:35 +00:00

cute_utils

[Kernel][SM100] Add a CuTeDSL fused query kernel (#49792 )

2026-08-04 15:23:06 -07:00

device_allocator

[Bugfix][CuMem] Make KV-cache wake cleanup tag-safe (#49857 )

2026-07-26 12:09:13 -07:00

distributed

[Hardware] Use torch.accelerator.empty_host_cache() for host cache cl… (#51107 )

2026-08-06 10:27:57 +08:00

engine

[Model] Fused mm preprocess normalisation on the Device (#50411 )

2026-08-06 03:11:14 -07:00

entrypoints

[Frontend] Watch frontend processes during engine startup (#43417 )

2026-08-06 11:17:24 -07:00

inputs

[Frontend][Core] Standardize request error handling with VLLMError hierarchy (#49665 )

2026-07-29 04:20:40 +00:00

ir

[CI] Use explicit devices in IR tests (#49513 )

2026-07-23 20:08:14 -07:00

kernels

[XPU] Unify XPU RMSNorm kernels with vllm_c and drop redundant XPU-specific implementation (#46981 )

2026-07-31 17:28:18 +08:00

logging_utils

…

lora

Fully generalise input embedding handling in Transformers modelling backend (#51247 )

2026-08-06 16:21:24 +00:00

model_executor

[ModelRunner v2] Enable decoder token-wise pooling (#50931 )

2026-08-06 22:21:52 +00:00

models

[Attention][MLA] Per-request scheduling for MLA chunked context (#50613 )

2026-08-06 16:45:44 +00:00

multimodal

[Bugfix][MM] Fix MiniCPM-V placeholder replacement and image processor loading on Transformers v5 (#48413 )

2026-08-05 21:12:00 -07:00

parser

[Model][Frontend] Add Ling 3.0 Flash BF16, MTP, and parser support (#51045 )

2026-08-06 00:38:28 +08:00

platforms

[CPU] Add MLA backend so DeepSeek-V2/V3 can run on CPU (#49453 )

2026-08-06 16:51:41 +08:00

plugins

[Frontend] Add endpoint plugins framework (#47454 )

2026-07-08 10:00:41 +08:00

profiler

[Refactor] Remove multiple dead codes (#50285 )

2026-08-03 10:59:08 -04:00

ray

Propagate Flash Attention cache configuration to Ray workers (#49177 )

2026-07-21 07:47:53 +00:00

reasoning

[Model][Frontend] Add Ling 3.0 Flash BF16, MTP, and parser support (#51045 )

2026-08-06 00:38:28 +08:00

renderers

[GPT-OSS] Strict tool call and constrained decoding for Harmony (#45560 )

2026-08-01 12:10:26 -04:00

third_party

[New model] Kimi K3 (#50000 )

2026-07-30 03:49:58 -07:00

tokenizers

[Frontend] DeepSeek V4 0731 reasoning effort prompts & mappings (#50580 )

2026-08-04 08:51:32 -07:00

tool_parsers

[Model][Frontend] Add Ling 3.0 Flash BF16, MTP, and parser support (#51045 )

2026-08-06 00:38:28 +08:00

tracing

…

transformers_utils

[Model] Fused mm preprocess normalisation on the Device (#50411 )

2026-08-06 03:11:14 -07:00

triton_utils

[ROCm] [Model] Enable TML inkling (#48841 )

2026-07-27 10:05:46 +00:00

usage

…

utils

[Core] Explicitly manage torch CPU threads in workers (#49919 )

2026-08-04 10:06:38 -07:00

v1

[ModelRunner v2] Enable decoder token-wise pooling (#50931 )

2026-08-06 22:21:52 +00:00

vllm_flash_attn

[2/N][Attention] Enable masked MHA for sparse MLA prefills (#48770 )

2026-07-31 06:01:24 -07:00

__init__.py

…

_aiter_ops.py

[ROCm] Enable AITER and FP8 inference on GFX120x (#43615 )

2026-08-03 16:45:37 -05:00

_custom_ops.py

[Attention][MiniMax-M3] Add MSA speculative decode verification (#50032 )

2026-08-02 13:46:55 -07:00

_xpu_ops.py

[XPU] Register fake meta kernel for fp4_gemm (#50946 )

2026-08-06 17:18:42 +08:00

collect_env.py

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

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

connections.py

…

env_override.py

[Perf] Add VLLM_TRITON_FORCE_FIRST_CONFIG to skip Triton autotuning (#42425 )

2026-06-16 15:16:45 +02:00

envs.py

[ROCm][MLA] Use asm decode for non-divisor small head counts (#50578 )

2026-08-06 14:56:53 -04:00

exceptions.py

[Frontend][Core] Standardize request error handling with VLLMError hierarchy (#49665 )

2026-07-29 04:20:40 +00:00

forward_context.py

[Feature] Support sequence parallel without the need for DP, 1.9%~5.0% E2E Throughput Improvement (#47070 )

2026-07-05 05:41:30 -07:00

logger.py

…

logits_process.py

…

logprobs.py

…

model_inspection.py

…

outputs.py

[Front-end] [Messages] Populate num_cache_creation_tokens (#48535 )

2026-07-18 13:04:35 -04:00

pooling_params.py

[Frontend][Core] Standardize request error handling with VLLMError hierarchy (#49665 )

2026-07-29 04:20:40 +00:00

py.typed

…

sampling_params.py

[Frontend][Core] Standardize request error handling with VLLMError hierarchy (#49665 )

2026-07-29 04:20:40 +00:00

scalar_type.py

Humming support for 2/3/5/6/7-bit pack-quantized weight-only inference (#46389 )

2026-06-24 13:53:54 -04:00

scripts.py

…

sequence.py

[Core] Cleanup KVConnector handling with PP + fix MRV2 (#43732 )

2026-05-28 13:12:03 -07:00

tasks.py

[Bugfix] Reject removed pooling parameters (#48984 )

2026-07-19 05:18:03 -07:00

version.py

…