vLLM/vllm at 79fd1bc7eda1854ba6b243c737ecc4bad74ffb84 - vLLM

assets

[Examples][last/6] Resettle examples. (#41084 )

2026-05-07 19:42:12 -07:00

benchmarks

Implement custom dataset class for ASR benchmarking (#41576 )

2026-05-12 12:17:58 +08:00

compilation

[ROCm] Run AITER RMSNorm pad fusion before AR RMS fusion (#42411 )

2026-05-13 18:35:12 +08:00

config

platforms: add uses_cpu_device() hook to Platform for DeviceConfig (#42313 )

2026-05-12 12:39:17 -07:00

device_allocator

Auto-disable expandable_segments around cumem memory pool (#40812 )

2026-04-27 09:37:22 +08:00

distributed

[kv_offload] Add req_id to ReqContext for per-request tracking (#42507 )

2026-05-13 11:11:10 +00:00

engine

[Performance] Make safetensors checkpoint prefetch settings configurable (#41499 )

2026-05-10 15:55:15 +00:00

entrypoints

[Bugfix][Frontend] Default max_tokens server-side on /inference/v1/generate (#42329 )

2026-05-13 11:16:46 +02:00

inputs

feat: Enable prompt_embeds Content Part Support in vLLM Chat Completions API (#40720 )

2026-05-01 10:05:55 +08:00

ir

[vLLM IR] Minor improvements (#39362 ) (#39558 )

2026-05-12 10:58:36 -04:00

kernels

[Kernel][Helion] Optimize Helion config parsing latency (#40850 )

2026-05-07 20:27:34 -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

[MoE Refactor] Introduce RoutedExperts alias for FusedMoE and don't store SharedExperts in MK (#40735 )

2026-05-12 13:37:44 -04:00

model_executor

[Bugfix][Qwen3-VL] Fix pipeline-parallel deepstack initialization (#42394 )

2026-05-13 10:58:42 +00:00

multimodal

[Bugfix] Fix scipy audio resampling ratio (#42233 )

2026-05-13 18:52:41 +08:00

parser

[Refactor] Consolidate required/named tool_choice streaming into DelegatingParser (#41876 )

2026-05-07 09:50:59 -07:00

platforms

platforms: add uses_cpu_device() hook to Platform for DeviceConfig (#42313 )

2026-05-12 12:39:17 -07:00

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

Fix: Nemotron 3 rescue whitespace-only final_content, not just None (#41846 )

2026-05-10 02:07:58 +00:00

renderers

[Bugifx] Missing Renderer for fastokens mode (#41984 )

2026-05-07 23:45:14 -07:00

third_party

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

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

tokenizers

tokenizer: Add fastokens support (#41741 )

2026-05-07 22:49:42 +08:00

tool_parsers

[Bugifx] [Qwen3CoderTool] Restore supports_required_and_named for required tool_choice (#42292 )

2026-05-12 02:09:56 +00:00

tracing

…

transformers_utils

Added peagle speculators support (#41826 )

2026-05-12 07:55:57 -07:00

triton_utils

[Feat][CPU] Enable Gated DeltaNet Attention (Qwen 3.5 / 3.6) (#41025 )

2026-05-07 12:57:09 +08:00

usage

…

utils

[MXFP4] Support for linear layers + compressed-tensors integration (#41664 )

2026-05-12 07:49:33 -04:00

v1

[kv_offload] Add req_id to ReqContext for per-request tracking (#42507 )

2026-05-13 11:11:10 +00:00

vllm_flash_attn

[Attention] use diff kv backend for mimo v2 flash (#40045 )

2026-04-24 11:25:55 +00:00

__init__.py

…

_aiter_ops.py

[ROCm][Perf] Add Fused Shared Expert (FSE) support for Qwen3-Next (#39280 )

2026-05-08 15:38:00 -04:00

_custom_ops.py

Use CU_MEMCPY_SRC_ACCESS_ORDER_ANY for batch KV cache swaps (#39306 )

2026-05-10 05:57:09 +03:00

_xpu_ops.py

[XPU] remove q/k/v force contiguous for flash_attn (#40356 )

2026-05-09 01:19:05 +00:00

beam_search.py

…

collect_env.py

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

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

connections.py

…

env_override.py

fix: default TILELANG_CLEANUP_TEMP_FILES=1 to avoid shared /tmp conflicts (#41486 )

2026-05-07 19:59:00 -07:00

envs.py

Add VLLM_USE_SPINLOOP_EXT to use more efficient busy polling (#36517 )

2026-05-11 16:11:49 -07:00

exceptions.py

…

forward_context.py

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

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

logger.py

…

logits_process.py

…

logprobs.py

…

model_inspection.py

…

outputs.py

[Core] Replace routing replay with device cache and async D2H pipeline (#39917 )

2026-05-07 11:24:56 -07:00

pooling_params.py

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

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

py.typed

…

sampling_params.py

[ROCm][CI] Skip ROCm batch invalid-input test pending torch fix (#41572 )

2026-05-13 18:50:47 +08:00

scalar_type.py

…

scripts.py

…

sequence.py

…

tasks.py

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

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

version.py

…