4 people 766b4ae54c [Kimi-K3] Add FlashInfer speculative KDA backend (#54255) ...

Signed-off-by: Duncan Moss <dmoss@nvidia.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Thien Tran <gau.nernst@yahoo.com.sg>

2026-10-01 02:28:50 +00:00

..

__init__.py

[MoE Refactor] FusedMoE/MoERunner inversion refactor (#41184)

2026-06-08 10:42:58 -04:00

argparse_utils.py

[Frontend] Add reusable TP1 initialized-engine snapshots (#51360)

2026-09-21 23:18:49 +00:00

async_utils.py

Add pydocstyle to the ruff rules (#52136)

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

b12x.py

[Kernel] Add B12X causal paged attention backend (#52017)

2026-09-01 10:42:02 -04:00

cache.py

Add pydocstyle to the ruff rules (#52136)

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

collection_utils.py

Add pydocstyle to the ruff rules (#52136)

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

counter.py

Add pydocstyle to the ruff rules (#52136)

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

cpu_resource_utils.py

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

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

cpu_triton_utils.py

[Feature] Triton kernel dispatcher (#43048)

2026-09-25 04:07:43 +00:00

deep_gemm.py

[Bugfix] prioritize architecture capability before DeepGEMM availability check (#58073)

2026-09-22 11:38:04 -04:00

diffusion.py

[Bugfix][CPU][DiffusionGemma] Support narrower canvas w/ sync scheduling (#59107)

2026-09-29 23:28:50 -04:00

flashinfer_moe_ep.py

[Model][MoE] DeepSeek-V4: add opt-in FlashInfer moe_ep expert backend (#49636)

2026-08-25 03:35:01 +00:00

flashinfer.py

[Kimi-K3] Add FlashInfer speculative KDA backend (#54255)

2026-10-01 02:28:50 +00:00

func_utils.py

Add pydocstyle to the ruff rules (#52136)

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

gc_utils.py

Add pydocstyle to the ruff rules (#52136)

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

gpu_sync_debug.py

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

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

hashing.py

Add pydocstyle to the ruff rules (#52136)

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

hpc.py

[Refactor] Remove utils dead code (#53941)

2026-09-08 11:22:09 -04:00

humming.py

[Feature][Humming] Humming feature integration (#56685)

2026-09-20 08:11:01 -07:00

import_utils.py

[Distributed][MoonEP] BF16 integration of MoonEP balanced EP backend (#52101)

2026-09-18 10:34:01 -04:00

jit_monitor.py

Add pydocstyle to the ruff rules (#52136)

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

jsontree.py

Add pydocstyle to the ruff rules (#52136)

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

math_utils.py

Add pydocstyle to the ruff rules (#52136)

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

mem_constants.py

[Tests] Add Qwen3-VL multimodal memory leak check (#39268)

2026-04-09 04:54:46 -07:00

mem_utils.py

Add pydocstyle to the ruff rules (#52136)

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

mistral.py

[PARSER][Mistral] unified engine-based parser for reasoning and tool calls (#48947)

2026-07-30 15:38:00 +02:00

multi_stream_utils.py

[ROCm][Perf] Enable layer-aware CSA2 multi-stream overlap for DeepSeek-V4.1-Flash (#57407)

2026-09-27 23:48:01 +08:00

nccl.py

[WideEP] Change DeepEPv2 to auto select hybrid mode by default (#57991)

2026-09-29 18:36:30 -04:00

network_utils.py

Add pydocstyle to the ruff rules (#52136)

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

numa_utils.py

[Bugfix][Core] Fall back when numactl --membind is blocked in constrained containers (#45438)

2026-06-16 09:49:56 -07:00

numa_wrapper.sh

[CI] replace shellcheck script with shellcheck-py hook (#52572)

2026-08-20 10:09:59 +00:00

nvtx_pytorch_hooks.py

Add pydocstyle to the ruff rules (#52136)

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

ompmultiprocessing.py

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

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

platform_utils.py

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

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

print_utils.py

[Examples][1/n] Resettle basic examples. (#35579)

2026-03-08 20:22:53 -07:00

registry.py

Add pydocstyle to the ruff rules (#52136)

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

serial_utils.py

[Frontend] Add routed-experts prompt offset (#51906)

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

sparse_utils.py

Add pydocstyle to the ruff rules (#52136)

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

system_utils.py

[Observability] log sub process killing in process manager force kill (#52314)

2026-09-30 06:13:24 +00:00

tensor_schema.py

Add pydocstyle to the ruff rules (#52136)

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

torch_utils.py

[XPU] Preserve non-contiguous strides when pinning CPU tensors for UVA view (#54874)

2026-09-29 09:43:07 +08:00

tqdm_utils.py

[Renderer] Move InputPreprocessor into Renderer (2/2) (#34560)

2026-02-17 05:29:01 -08:00