Michael Goin a8bffaa133 [Kernel] Add MXFP4 W4A4 CUTLASS MoE kernel for SM100 (#37463) ...

Signed-off-by: mgoin <mgoin64@gmail.com>

2026-04-17 16:42:32 -07:00

..

kernels

[Bugfix] Add Marlin kernel in block scaled mm kernel selection. (#40105)

2026-04-17 10:20:32 +00:00

layers

[Kernel] Add MXFP4 W4A4 CUTLASS MoE kernel for SM100 (#37463)

2026-04-17 16:42:32 -07:00

model_loader

[Quantization] - Layerwise reloading of Attention/KV quantized models (#38995)

2026-04-15 18:03:32 -07:00

models

feat: Add LoRA support for Gemma4ForConditionalGeneration (#39291)

2026-04-17 09:39:19 -07:00

offloader

[Bugfix] Respect VLLM_WEIGHT_OFFLOADING_DISABLE_PIN_MEMORY in prefetch offloader (#37699)

2026-04-14 20:43:29 -07:00

warmup

[MoE] Move DEEP_GEMM into experts/ subdirectory (#39005)

2026-04-08 19:23:08 +00:00

__init__.py

[Platform] Deprecate seed_everything (#31659)

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

custom_op.py

Add ability to replace oot ops when using lora (#37181)

2026-03-16 18:04:15 -07:00

parameter.py

[Mypy] Fix mypy for vllm/model_executor (except vllm/model_executor/layers) (#37904)

2026-03-24 17:14:01 +00:00

utils.py

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

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