Woosuk KwonandCodex 80447d2765 [Bugfix][DSv4.1] Fix FlashInfer DSpark non-causal attention (#57432) ...

Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Codex <noreply@openai.com>

2026-09-17 15:14:37 -07:00

..

assets

Add pydocstyle to the ruff rules (#52136)

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

benchmarks

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

compilation

[Mypy] Fix mypy typing for Transformers models (#54320)

2026-09-17 12:11:31 -04:00

config

[Bugfix] Max-load throughput cliff when max_num_seqs is not a multiple of 8 (#57355)

2026-09-17 18:09:18 +00:00

cute_utils

[5/N][warmup][DSv4] Migrate NVIDIA CuTeDSL attention kernels (#53566)

2026-09-12 00:05:59 -04:00

device_allocator

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

distributed

[Bugfix][HiSparse][NIXL] Import full blocks without tail prefill on D (#57049)

2026-09-17 15:26:10 -04:00

engine

[Scheduler] Add --max-num-active-seqs to cap RUNNING admission (#56758)

2026-09-17 10:22:12 +08:00

entrypoints

[Bugfix][Frontend] Reject stop strings on --tokens-only servers instead of silently ignoring them (#57058)

2026-09-17 22:02:00 +00:00

inputs

Add pydocstyle to the ruff rules (#52136)

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

ir

Add pydocstyle to the ruff rules (#52136)

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

kernels

Add pydocstyle to the ruff rules (#52136)

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

logging_utils

Add pydocstyle to the ruff rules (#52136)

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

lora

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

model_executor

[MoE] Encapsulate TRT-LLM BF16 weight layout handling (#57405)

2026-09-17 17:47:30 -04:00

models

[Bugfix][DSv4.1] Fix FlashInfer DSpark non-causal attention (#57432)

2026-09-17 15:14:37 -07:00

multimodal

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

parser

[Refactor] Remove unused interface methods (#57194)

2026-09-16 21:00:48 +00:00

platforms

[CPU] Align scheduler and NIXL CPU affinity per local rank (#53636)

2026-09-17 16:43:08 +08:00

plugins

Add pydocstyle to the ruff rules (#52136)

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

profiler

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

ray

Add pydocstyle to the ruff rules (#52136)

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

reasoning

[Kimi K3 Bug] Fix kimi k3 reasoning parser (#57098)

2026-09-17 10:05:52 -07:00

renderers

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

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

Add pydocstyle to the ruff rules (#52136)

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

tool_parsers

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

tracing

Add pydocstyle to the ruff rules (#52136)

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

transformers_utils

Fix Laguna patch mutating flat RoPE parameters (#57189)

2026-09-17 12:22:57 +00:00

triton_utils

[Bugfix][CPU] Fix several bugs (#54042)

2026-08-31 15:33:06 +08:00

usage

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

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

utils

[DSv4.1] Integrate Mega-Gate from DeepGEMM (#56266)

2026-09-17 12:06:36 -07:00

v1

[Bugfix][DSv4.1] Fix FlashInfer DSpark non-causal attention (#57432)

2026-09-17 15:14:37 -07:00

vllm_flash_attn

Add pydocstyle to the ruff rules (#52136)

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

__init__.py

Add pydocstyle to the ruff rules (#52136)

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

_aiter_ops.py

[ROCm] Restore VLLM_ROCM_USE_AITER_FP4_ASM_GEMM and default w4a4 ASM GEMM back to off (#57055)

2026-09-17 13:39:52 -05:00

_custom_ops.py

Add pydocstyle to the ruff rules (#52136)

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

_xpu_ops.py

Add pydocstyle to the ruff rules (#52136)

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

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

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

envs.py

[ROCm] Restore VLLM_ROCM_USE_AITER_FP4_ASM_GEMM and default w4a4 ASM GEMM back to off (#57055)

2026-09-17 13:39:52 -05:00

exceptions.py

Add pydocstyle to the ruff rules (#52136)

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

forward_context.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

logger.py

[CI] Support FORCE_COLOR env var; enable colors in CPU CI output (#56913)

2026-09-16 22:40:21 -04:00

logits_process.py

…

logprobs.py

Add pydocstyle to the ruff rules (#52136)

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

model_inspection.py

…

outputs.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +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

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

scalar_type.py

Add pydocstyle to the ruff rules (#52136)

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

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

…