EdalatiAli e5b807607c [Quant][Feature] Support online MXFP8 quantization for MoE and dense models (#35448) ...

Signed-off-by: EdalatiAli <aliedalati@cohere.com>

2026-03-16 18:07:39 -04:00

..

kernels

[Misc] Use envs module to get VLLM_DISABLED_KERNELS (#35776)

2026-03-11 13:37:46 +00:00

layers

[Quant][Feature] Support online MXFP8 quantization for MoE and dense models (#35448)

2026-03-16 18:07:39 -04:00

model_loader

[Performance] Add prefetch for checkpoints to OS page cache (#36012)

2026-03-16 11:32:02 +00:00

models

[torch.compile][BE] Modify cudagraph callable to check for is_forward_context_set (#36288)

2026-03-16 19:42:34 +00:00

offloader

[UX] Remove NoOpOffloader log (#35678)

2026-03-04 12:13:40 -08:00

warmup

[Feature]: Remove Chunking From FusedMoE (#34086)

2026-03-12 14:24:38 -04:00

__init__.py

[Platform] Deprecate seed_everything (#31659)

2026-01-04 18:34:04 -08:00

custom_op.py

[MM][OOT] Support CPU seq_lens for OOT MMEncoderAttention kernels (#36605)

2026-03-12 03:28:23 -07:00

parameter.py

[QeRL] Layerwise Reloading (#32133)

2026-01-30 08:50:05 -07:00

utils.py

[BugFix] Fix EPLB fail for MoeFP4 model with Marlin backend (#33262)

2026-01-29 16:52:11 +08:00