Danielle RobinsonandDanielle Robinson 74898a7015 [BugFix][LoRA] TritonExperts is ModularMoEPath for FP8 models (#33393) ...

Signed-off-by: Danielle Robinson <dmmaddix@amazon.com>
Co-authored-by: Danielle Robinson <dmmaddix@amazon.com>

2026-01-30 15:27:42 +00:00

..

__init__.py

Add support for LoRA adapters in Nemotron-H models (#30802)

2026-01-19 22:30:44 +08:00

base_linear.py

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

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

base.py

[LoRA] Continue optimizing MoE LoRA weight loading (#29322)

2025-11-27 05:56:28 -08:00

column_parallel_linear.py

Add support for LoRA adapters in Nemotron-H models (#30802)

2026-01-19 22:30:44 +08:00

fused_moe.py

[BugFix][LoRA] TritonExperts is ModularMoEPath for FP8 models (#33393)

2026-01-30 15:27:42 +00:00

logits_processor.py

[LoRA] Continue optimizing MoE LoRA weight loading (#29322)

2025-11-27 05:56:28 -08:00

replicated_linear.py

[LoRA] Continue optimizing MoE LoRA weight loading (#29322)

2025-11-27 05:56:28 -08:00

row_parallel_linear.py

[LoRA] Continue optimizing MoE LoRA weight loading (#29322)

2025-11-27 05:56:28 -08:00

utils.py

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

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

vocal_parallel_embedding.py

[LoRA] Continue optimizing MoE LoRA weight loading (#29322)

2025-11-27 05:56:28 -08:00