Nick Hill f2aad6aa70 [MRV2] Buffer util simplifications (#56888) ...

Signed-off-by: Nick Hill <nickhill123@gmail.com>

2026-09-15 20:36:51 +00:00

..

autoregressive

[BugFix] Fix DP token padding in dflash attention metadata (#56181)

2026-09-11 14:33:53 -07:00

dflash

[MRV2] Revert explicit Triton JIT warmup migration (#56654)

2026-09-13 04:07:56 +00:00

dflash2

[Model Runner V2] Acceptance estimation for adaptive verification (#52228)

2026-09-14 15:58:48 -07:00

dspark

[Bugfix][Spec Decode][MoE] Avoid uninitialized EPLB state in DeepSeek V4.1 DSpark drafter (#56387)

2026-09-15 14:35:47 +00:00

eagle

[Bugfix][Spec Decode] Avoid fastsafetensors deadlock for PP draft models (#54416)

2026-09-12 14:22:30 +08:00

gemma4

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

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

mtp

[PCP][Spec Decode] Adds PCP support for single-module MTP and replicated DSpark. (#56107)

2026-09-10 22:07:53 -07:00

multi_module_mtp

[MRV2] Revert explicit Triton JIT warmup migration (#56654)

2026-09-13 04:07:56 +00:00

__init__.py

[Spec Decode] DFlash2: local convolution + candidate selector (#52816)

2026-08-20 22:27:22 -07:00

acceptance_estimator.py

[Model Runner V2] Acceptance estimation for adaptive verification (#52228)

2026-09-14 15:58:48 -07:00

adaptive_verification.py

[MRV2] Buffer util simplifications (#56888)

2026-09-15 20:36:51 +00:00

extract_hidden_states.py

[Model Runner V2][Spec Decode] Skip DP sync before EAGLE/MTP draft prefill (#53694)

2026-08-26 20:59:35 -07:00

rejection_sampler_utils.py

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

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

rejection_sampler.py

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

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

speculator.py

[Model Runner V2] Acceptance estimation for adaptive verification (#52228)

2026-09-14 15:58:48 -07:00

utils.py

[Bugfix][Spec Decode] Avoid fastsafetensors deadlock for PP draft models (#54416)

2026-09-12 14:22:30 +08:00