bnellnmandRobert Shaw 726efe177b [MoE Refactor] Move the shared/fused expert output sum into MoERunnerBase (#35949) ...

Signed-off-by: Bill Nell <bnell@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>

2026-04-20 12:28:46 -04:00

..

__init__.py

Revert "[Kernel] Add gpt-oss Router GEMM kernel (#37205)" (#38778)

2026-04-01 22:02:32 -07:00

base_linear.py

[LoRA] Support dual CUDA streams-Linear Layer (#35721)

2026-04-13 10:57:07 +08:00

base.py

[CI] Bump mypy version to 1.19.1 (#36104)

2026-03-10 09:18:28 -07:00

column_parallel_linear.py

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

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

fused_moe.py

[MoE Refactor] Move the shared/fused expert output sum into MoERunnerBase (#35949)

2026-04-20 12:28:46 -04:00

logits_processor.py

[Bugfix] Remove erroneous lower bound on LoRA vocab size constraint (#35354)

2026-02-26 18:44:50 +00:00

replicated_linear.py

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

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

row_parallel_linear.py

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

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

utils.py

[Quantization][Deprecation] Deprecate HQQ (#32681)

2026-01-21 09:32:40 -05:00

vocal_parallel_embedding.py

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

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