3 people 458334f00f [MRV2][Spec Decode] Close DFlash/DSpark and adaptive-verification JIT warmup gaps (#63819) ...

Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: vllm-agent <claw@inferact.ai>

2026-10-28 01:15:00 +00:00

..

assets

[MyPy][4/N] Fix mypy errors in medium-hard tests/ dirs (#55485)

2026-10-20 04:51:15 -07:00

benchmarks

[Bugfix][Bench] Support Muse balanced routing (#63872)

2026-10-27 17:50:19 -07:00

compilation

[ROCm][aiter] officially supporting aiter Triton kernels+dsv4 on RDNA3 (#52970)

2026-10-27 17:01:13 +00:00

config

[Feature][Core] Enable best-effort NUMA binding by default (#61258)

2026-10-27 22:36:02 +01:00

cute_utils

[Bugfix] Support CuTe DSL 4.8.0 block-scale API (#59480)

2026-10-01 02:30:06 +00:00

device_allocator

[Core][Sleep Mode] Use torch.accelerator in CuMemAllocator free/sleep (#62701)

2026-10-22 11:56:18 +08:00

distributed

[Feature][HiSparse] Add a platform backend for device operations (#62592)

2026-10-27 21:18:40 +00:00

engine

[Feature][Core] Enable best-effort NUMA binding by default (#61258)

2026-10-27 22:36:02 +01:00

entrypoints

[Core][Frontend] Process checkpoint lifecycle with HTTP prepare/status/resume (#62570)

2026-10-27 08:02:44 +00:00

inputs

Remove Python 3.10 support now that it is EOL (#60402)

2026-10-08 02:30:52 -07:00

ir

Add pydocstyle to the ruff rules (#52136)

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

kernels

[ROCm][Perf] Fix Gemma AR+RMS prefill fallback (#58547)

2026-10-12 19:53:08 +00:00

logging_utils

[Core][Logging] Add built-in JSON formatter (#58739)

2026-10-01 09:11:46 +01:00

lora

[Bugfix][LoRA] Avoid double rounding in fused MoE expand (#63894)

2026-10-27 10:09:57 +00:00

model_executor

[Perf] Use TMA for MOE up/down proj, 3.1~3.4% E2E Throughput Improvement for GLM5.3 (#63820)

2026-10-27 18:21:39 -04:00

models

[Bugfix][Kimi-K3] Reserve KDA prefill workspace before profiling (#63989)

2026-10-28 05:35:07 +07:00

multimodal

[Bugfix][Multimodal] Return 400 when local media access is disabled (#64032)

2026-10-27 13:21:21 +00:00

parser

[Tool Calling] Migrate llama3_json parser to parser engine (#63569)

2026-10-26 22:30:20 +00:00

platforms

[Feature][HiSparse] Add a platform backend for device operations (#62592)

2026-10-27 21:18:40 +00:00

plugins

[Bugfix][Frontend] Honor endpoint plugin route overrides (#58839)

2026-10-12 03:58:15 +00:00

profiler

[Profiling] Add support for profile_prefix payload in HTTP /start_profile endpoint (#51974)

2026-10-24 13:22:11 -07:00

ray

Add pydocstyle to the ruff rules (#52136)

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

reasoning

[Model][ROCm] Add Muse Spark Open support on ROCm (#62622)

2026-10-22 17:00:09 +08:00

renderers

[Frontend][Mistral] Forward response_format to mistral-common chat templating (#63812)

2026-10-27 04:39:11 +00:00

snapshot

[Frontend] Consolidate startup utils. (#62390)

2026-10-19 16:00:10 +00:00

third_party

[Perf] Tune the Triton packed GDN decode tile on SM90 (#63864)

2026-10-27 07:17:34 +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

[Frontend][Mistral] Forward response_format to mistral-common chat templating (#63812)

2026-10-27 04:39:11 +00:00

tool_parsers

[Tool Calling] Migrate llama3_json parser to parser engine (#63569)

2026-10-26 22:30:20 +00:00

tracing

Add pydocstyle to the ruff rules (#52136)

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

transformers_utils

[UX] Remove --hf-overrides necessity for Qwen3-ASR-ForceAligner (#63274)

2026-10-27 23:20:03 +08:00

triton_utils

[Bugfix] Forward launch grid to Triton kernel overrides (#63999)

2026-10-27 14:46:07 +00:00

usage

Remove Python 3.10 support now that it is EOL (#60402)

2026-10-08 02:30:52 -07:00

utils

[Feature][Core] Enable best-effort NUMA binding by default (#61258)

2026-10-27 22:36:02 +01:00

v1

[MRV2][Spec Decode] Close DFlash/DSpark and adaptive-verification JIT warmup gaps (#63819)

2026-10-28 01:15:00 +00:00

vllm_flash_attn

[Bugfix][Attention] Fix FA4 FP8 descale strides for singleton KV heads (#58304)

2026-10-22 14:36:00 -04:00

__init__.py

Add pydocstyle to the ruff rules (#52136)

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

_aiter_ops.py

[ROCm][aiter] officially supporting aiter Triton kernels+dsv4 on RDNA3 (#52970)

2026-10-27 17:01:13 +00:00

_custom_ops.py

[Bugfix][MLA] Gather nvfp4_ds_mla chunked-context KV with the NVFP4 kernel (#58744)

2026-10-27 14:35:01 -04:00

_xpu_ops.py

[XPU][MLA] Integrate XPU MLA support into the existing FLASH_ATTN_MLA backend (#58297)

2026-10-15 12:47:37 +08:00

collect_env.py

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

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

connections.py

[Multimodal][Docs] State that retried media downloads count toward the request budget (#62204)

2026-10-19 02:36:29 +00:00

env_override.py

[Bugfix][Platform] Keep PIN_MEMORY eager; avoid resolving platform during import vllm (#63601)

2026-10-26 03:09:30 +00:00

envs.py

[MoE] Add locality-domain allocation for FlashInfer CuTeDSL NVFP4 (#61685)

2026-10-26 14:37:01 -04:00

exceptions.py

[Misc] Break chat_utils into more maintainable modules. (#60972)

2026-10-13 15:08:07 +00:00

forward_context.py

[Bugfix][MoE] Restore TP-sharded routed-expert capture for DP=1 (#61388)

2026-10-16 00:21:24 +00:00

logger.py

[Core][Logging] Add built-in JSON formatter (#58739)

2026-10-01 09:11:46 +01:00

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

[Bugfix] Reject mixed structured output backends during validation (#49625)

2026-10-20 21:13:13 +03:00

pooling_params.py

[Bugfix][Pooling] Validate late-interaction mode and use count in the Python API (#63112)

2026-10-23 05:45:15 +00:00

py.typed

…

sampling_params.py

[Bugfix] Bound prefix cache reuse by the first requested prompt score (#60960)

2026-10-27 19:26:07 +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

sequence.py

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

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

tasks.py

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

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

version.py

[CI] Allowlist-shrink batch 1: wire 17 root-level tests + drop 5 stale watermarking entries into misc.yaml (#58055)

2026-09-27 22:23:46 -07:00