3 people f38c6778ce [quantization] Add per-token NVFP4 quantization MoE support for ReLU2 (#56740) ...

Signed-off-by: Xuanteng Huang <xuantengh@nvidia.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>

2026-10-07 22:01:09 +00:00

..

__init__.py

[Core] Model console logging as CLI configuration (#57205)

2026-09-25 11:36:59 +01:00

attention.py

[ROCm][DSv4.1] Paged MXFP4 sparse indexer on aiter's MQA-logits kernel (#58671)

2026-09-29 14:37:57 +08:00

aux_output.py

[AuxOutput] Add block-keyed storage for routed-expert outputs (#45635)

2026-09-21 10:25:05 +00:00

cache.py

[Attention] Add UltraQuant 4-bit KV cache backend (FlyDSL D=256) (#57057)

2026-10-06 20:42:52 +00:00

compilation.py

[Bugfix] Respect Inductor deterministic mode in combo-kernel defaults (#59074)

2026-10-07 20:08:11 +01:00

device.py

Add pydocstyle to the ruff rules (#52136)

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

diffusion.py

[Model] Add DiffusionGemma Support (#45163)

2026-06-11 22:17:35 -07:00

ec_manager_config.py

Add pydocstyle to the ruff rules (#52136)

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

ec_transfer.py

[Refactor] Remove dead env and config (#59781)

2026-10-02 18:07:20 +00:00

engram.py

[Config] Remove Engram CUDA-alike device restrictions (#59171)

2026-09-29 12:42:02 +00:00

fault_tolerance.py

[Feature] Add fault tolerance framework (simplified) for DP+EP external LB deployments (#44428)

2026-07-25 11:49:09 -04:00

kernel.py

[ROCm][DSv4] AITER MegaMoEV2 Integration For DeepSeek V4 (#59685)

2026-10-07 09:35:53 -05:00

kv_events.py

[Mypy] Better fixes for the mypy issues in vllm/config (#37902)

2026-03-25 06:14:43 -07:00

kv_transfer.py

[Refactor] Remove dead env and config (#59781)

2026-10-02 18:07:20 +00:00

load.py

[UX][Frontend] Introduce vllm preload cli for fast restart (#56680)

2026-09-25 06:56:39 +00:00

logging.py

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

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

lora.py

[LoRA] Code cleanup (#60017)

2026-10-05 09:15:53 +00:00

mamba.py

[Kernel] Add support for Flashinfer Mamba SSU algorithm selection (#50157)

2026-08-04 09:40:23 -07:00

model_arch.py

Add pydocstyle to the ruff rules (#52136)

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

model.py

feat: Add video support for the Transformers backend (#57441)

2026-10-05 00:51:15 -07:00

multimodal.py

[Bugfix] Warn only on per-request do_normalize/do_rescale overrides (#60240)

2026-10-06 15:55:27 +00:00

observability.py

[Metrics] Add --custom-histogram-buckets to override histogram bucket families (#48867)

2026-10-01 01:03:39 +00:00

offload.py

Add pydocstyle to the ruff rules (#52136)

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

parallel.py

[EPLB] Add contention-aware expert migration batching (#52641)

2026-10-03 00:13:50 +00:00

pooler.py

[Perf] Integrate flash-maxsim Triton kernels for late-interaction scoring (#40337)

2026-10-01 14:06:43 -04:00

profiler.py

[Profiler] Add per-session profiling controls to Python and Rust frontends (#57875)

2026-10-06 05:21:19 +00:00

quantization.py

[quantization] Add per-token NVFP4 quantization MoE support for ReLU2 (#56740)

2026-10-07 22:01:09 +00:00

reasoning.py

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

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

scheduler.py

[Scheduler] Tune --long-prefill-token-threshold adaptiveness (#58459)

2026-09-23 22:23:18 -04:00

speculative.py

[ModelRunner V2] Speculative Decoding NGram GPU Implementations (#40704)

2026-10-06 13:32:59 -07:00

speech_to_text.py

support hotwords for FunASR model (#39674)

2026-04-22 02:25:06 -07:00

structured_outputs.py

Add pydocstyle to the ruff rules (#52136)

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

utils.py

[Bugfix][CLI] Include inherited field docstrings in get_attr_docs (#49821)

2026-10-01 23:35:58 +00:00

vllm.py

[ModelRunner V2] Speculative Decoding NGram GPU Implementations (#40704)

2026-10-06 13:32:59 -07:00

watermarking.py

[watermarking] Dual-key gumbel-max watermarking for speculative decoding support (#56122)

2026-09-12 18:42:01 +00:00

weight_transfer.py

[RL] Add sharding-aware NCCL M2N weight transfer (#51520)

2026-09-26 01:38:53 +00:00