Itay AlroyandTyler Michael Smith bdea2777ea [Bugfix][MoE] Fix batched CUTLASS workspace overallocation (#55579) ...

Signed-off-by: Itay Alroy <ialroy@nvidia.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>

2026-09-10 15:33:56 +00:00

..

assets

…

benchmarks

[Bugfix] Reject 0 or non-positive max concurrency (#54887)

2026-09-04 15:59:29 -04:00

compilation

[Kernel] Enable optimized FlashInfer add-RMSNorm NVFP4 fusion (#51925)

2026-09-08 17:20:32 -07:00

config

[Feature][Spec Decode] MTP with separate (possibly quantized) lm head for nemotron (#54574)

2026-09-10 08:26:31 -04:00

cute_utils

[Kimi-K3] Add GEMM-RS for sequence parallelism (#52079)

2026-08-13 09:02:28 -07:00

device_allocator

[Core] Release NCCL communicator memory in sleep mode (#51485)

2026-09-01 14:31:16 +08:00

distributed

[NIXL][PCP] Report replicated-PCP ranks > 0 as done sending instead of hiding them (#53903)

2026-09-10 12:58:05 +02:00

engine

[ROCm][Perf] Kimi-K3 Fused kernels for KDA prefill reland (#54038)

2026-09-10 15:37:54 +08:00

entrypoints

[Bugfix] Honor explicit empty and zero CLI arguments (#55710)

2026-09-10 15:07:42 +00:00

inputs

[Feat][MM Hashing] include media_io_kwargs in multi-modal hashes (#54241)

2026-09-01 13:17:01 +00:00

ir

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

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

kernels

[Kernel] Remove unused fake implementation (#55535)

2026-09-06 17:54:32 -07:00

logging_utils

…

lora

[Bugfix][LoRA] Log when an adapter applies no weights (#55310)

2026-09-09 17:44:46 +00:00

model_executor

[Bugfix][MoE] Fix batched CUTLASS workspace overallocation (#55579)

2026-09-10 15:33:56 +00:00

models

[Fast Start] Support fp4 (#55465)

2026-09-10 13:22:17 +00:00

multimodal

[multimodal][feat] add torchaudio backend to AudioResampler (#52598)

2026-09-10 06:42:38 +00:00

parser

[Model] Add Bailing V3 VL support (#55921)

2026-09-10 02:46:56 -07:00

platforms

[ROCm] Add better kv dtype error discoverability (#55236)

2026-09-10 09:17:41 +00:00

plugins

[MISC] Cleanup deprecated parameters (#53559)

2026-08-24 10:19:04 -07:00

profiler

[Profiler] Fix start_profile permanently no-op after max_iterations auto-stop (#51839)

2026-08-25 08:13:29 -04:00

ray

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

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

reasoning

[Model][Frontend] Support DeepSeek-V4.1-Flash in Rust and Python frontends (#56208)

2026-09-10 01:15:06 -07:00

renderers

[Model][Frontend] Support DeepSeek-V4.1-Flash in Rust and Python frontends (#56208)

2026-09-10 01:15:06 -07:00

third_party

[Kernel] Warm up Qwen GDN gated RMSNorm (#54251)

2026-09-03 18:19:48 +08:00

tilelang_utils

[ROCm] Defer tilelang import through its import from vllm.tilelang_utils import tilelang and relaxed has_tilelang (#51159)

2026-08-13 13:12:40 -05:00

tokenizers

[Model][Frontend] Support DeepSeek-V4.1-Flash in Rust and Python frontends (#56208)

2026-09-10 01:15:06 -07:00

tool_parsers

[Model][Frontend] Support DeepSeek-V4.1-Flash in Rust and Python frontends (#56208)

2026-09-10 01:15:06 -07:00

tracing

…

transformers_utils

[Model] Add Bailing V3 VL support (#55921)

2026-09-10 02:46:56 -07:00

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

[Fast Start] Support fp4 (#55465)

2026-09-10 13:22:17 +00:00

v1

[CI/Build][CPU] Fix flaky rust downloads, broken prune flag, and triton-cpu cache coupling (#56247)

2026-09-10 22:27:26 +08:00

vllm_flash_attn

Revert "[Kernel] Gemma-4 FA4 FP8 Kernel" (#52987)

2026-08-19 10:48:46 -07:00

__init__.py

…

_aiter_ops.py

[ROCm][Perf][M3] Fused allreduce+GemmaRMSNorm fast path (#54787)

2026-09-08 07:21:49 +00:00

_custom_ops.py

[Model] Add DeepSeek-V4 CPU backend (#55355)

2026-09-10 14:14:48 +08:00

_xpu_ops.py

[XPU] Use fused_input_norm kernel in FusedInputNorm (#52945)

2026-09-07 13:44:31 +08:00

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

…

envs.py

[Qwen4Exp] Support UVA PLE-offload and Engram tensor parallelism (#54371)

2026-09-09 07:32:34 -07:00

exceptions.py

[Core] Add max_num_queued_reqs and max_num_queued_tokens for queue size management (#49445)

2026-08-31 14:26:49 +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

[Bugfix] Handle empty FlatLogprobs slices and delta output (#53704)

2026-08-26 21:00:54 +08:00

model_inspection.py

…

outputs.py

[Frontend][Core][Spec Decode] Per-request acceptance stats in OpenAI API responses (#48915)

2026-08-20 15:42:49 -07:00

pooling_params.py

[MISC] Cleanup deprecated parameters (#53559)

2026-08-24 10:19:04 -07:00

py.typed

…

sampling_params.py

[feature] Watermarked generation and detection (Gumbel-max algorithm) (#54053)

2026-09-09 21:00:15 -07:00

scalar_type.py

…

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

…