Samuel NordmannandCodex d08eebad16 [Perf][MoE] Write FlashInfer combine into final output (#47156) ...

Signed-off-by: snordmann <snordmann@nvidia.com>
Co-authored-by: Codex <codex@openai.com>

2026-07-16 17:21:03 +03:00

..

kernels

[ROCm][BugFix] Triton W4A16 handling for GPTQ/AutoGPTQ qzeros layout (#47770)

2026-07-15 11:55:47 -05:00

layers

[Perf][MoE] Write FlashInfer combine into final output (#47156)

2026-07-16 17:21:03 +03:00

model_loader

[CI][AMD] Configure MI300 tests for native execution without DinD (#48387)

2026-07-15 02:14:16 +00:00

models

[Model] Add Inkling model support [1/N] (#48799)

2026-07-15 23:40:07 -07:00

offloader

Revert "[Platform] Replace torch.cuda.Event with torch.Event (#47140)" (#47668)

2026-07-06 14:18:33 +01:00

warmup

[Model] Add Inkling model support [1/N] (#48799)

2026-07-15 23:40:07 -07:00

__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

Speed up docs build (#44635)

2026-06-05 14:51:44 +00:00

utils.py

Remove more unnecessary load_weights methods (#47058)

2026-06-30 15:22:16 +01:00