vLLM/vllm at fe57be7809672e5c4d100b55ce8649dd34d3bbc0 - vLLM

assets

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

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

benchmarks

[Bugfix] Fix dataset name and path argument validation bug in vllm bench serve (#40288 )

2026-04-21 06:14:28 -07:00

compilation

[compile] Skip FX graph deserialiaztion on loading, further reducing warm compile time. (#40151 )

2026-04-23 13:43:18 +08:00

config

[Refactor] Clean up log once scope="local" (#40540 )

2026-04-22 16:42:43 -04:00

device_allocator

…

distributed

[Fix][MoRI] Align MoRI-IO message format with P2pNcclConnector and vllm-router (#39565 )

2026-04-23 08:06:31 +09:00

engine

[Refactor] Clean up log once scope="local" (#40540 )

2026-04-22 16:42:43 -04:00

entrypoints

[Responses] Add tool_choice/tools validation to match OpenAI behavior (#40399 )

2026-04-22 22:46:10 -07:00

inputs

[Misc] Reorganize inputs (#35182 )

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

ir

[vLLM IR] Add IR op testing and benchmarking infrastructure (#40167 )

2026-04-21 00:23:03 +00:00

kernels

[Kernel] [Helion] Force disable HOP path due to performance regression (#40171 )

2026-04-17 17:36:49 -04:00

logging_utils

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

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

lora

[Refactor] Clean up log once scope="local" (#40540 )

2026-04-22 16:42:43 -04:00

model_executor

[MM][CG] Support --enable-vit-cuda-graph option for VLM examples (#40580 )

2026-04-22 22:46:14 -07:00

multimodal

[Multimodal] Support custom video metadata for pre-extracted frame sequences (#40133 )

2026-04-22 15:50:04 +08:00

parser

[Bugfix] Accept **kwargs in MiniMaxM2Parser.__init__() (#39861 )

2026-04-16 15:18:32 +08:00

platforms

[XPU] disable fusion pattern support on XPU platform (#39789 )

2026-04-23 10:07:45 +08:00

plugins

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

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

profiler

[Refactor] Clean up log once scope="local" (#40540 )

2026-04-22 16:42:43 -04:00

ray

…

reasoning

[Bugfix] [Reasoning] Add reasoning_start_str/reasoning_end_str properties to reasoning parsers (#40566 )

2026-04-22 07:27:44 +00:00

renderers

[Bugfix] avoid warmup if text only expectation in multi_modal run (#40409 )

2026-04-22 00:19:50 +00:00

third_party

…

tokenizers

[Mistral Grammar] Fix tool and reasoning parsing (#39217 )

2026-04-15 21:05:04 -07:00

tool_parsers

[Bugfix][Parser] Fix Mistral pre-v11 tool parser failing on trailing model output (#40531 )

2026-04-22 16:35:00 -04:00

tracing

…

transformers_utils

Add Granite 4.1 Vision as built-in multimodal model (#40282 )

2026-04-21 05:43:39 -07:00

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

[Refactor] Clean up log once scope="local" (#40540 )

2026-04-22 16:42:43 -04:00

v1

[TurboQuant] enable FA3/FA4 for prefill paths (#40092 )

2026-04-23 07:35:24 +03:00

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

…

_aiter_ops.py

[ROCm] Hotfix: guard MLA dual RMS norm fusion against older AITer versions (#40386 )

2026-04-20 16:20:05 -05:00

_custom_ops.py

[Perf] Optimize batch invariant with fused rms norm, 2.1% E2E latency improvement (#40413 )

2026-04-21 19:51:03 +00:00

_oink_ops.py

…

_xpu_ops.py

[XPU]fake impl for xpu fp8_gemm (#39984 )

2026-04-18 08:53:56 +08:00

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

Fix test_startup.py for torch 2.12 (#40636 )

2026-04-22 19:31:41 +00:00

envs.py

[Multimodal] Add PyAV video backend for concurrent video decoding (#39986 )

2026-04-21 20:14:57 -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

[MoE Refactor] Remove MoE DP chunking (#39107 )

2026-04-14 09:48:05 -04:00

logger.py

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

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

logits_process.py

…

logprobs.py

…

model_inspection.py

…

outputs.py

…

pooling_params.py

[Frontend] Remove frontend pooling multi task support. (#37861 )

2026-04-21 12:27:44 +00:00

py.typed

…

sampling_params.py

[Mistral Grammar] Fix tool and reasoning parsing (#39217 )

2026-04-15 21:05:04 -07:00

scalar_type.py

…

scripts.py

…

sequence.py

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

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

tasks.py

[Frontend] Remove frontend pooling multi task support. (#37861 )

2026-04-21 12:27:44 +00:00

version.py

…