baonudesifeizhai 1fb648bf10 [Bugfix] Fix FP8 MoE EP Weight Loading for ModelOpt Llama4 (#32886) ...

Signed-off-by: baonudesifeizhai <baonudesifeizhai@gmail.com>

2026-01-23 10:31:48 -05:00

..

layers

[Bugfix] Disable tma_aligned_scales in test_fusions_e2e (#32916)

2026-01-23 14:34:30 +00:00

model_loader

Add llmcompressor fp8 kv-cache quant (per-tensor and per-attn_head) (#30141)

2026-01-22 13:29:57 -07:00

models

[Bugfix] Fix FP8 MoE EP Weight Loading for ModelOpt Llama4 (#32886)

2026-01-23 10:31:48 -05:00

warmup

[MoE Refactor] Oracle Select FP8+NVFP4 Kernels In Priority (#32414)

2026-01-21 08:22:33 -05:00

__init__.py

[Platform] Deprecate seed_everything (#31659)

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

custom_op.py

[torch.compile] Compile CustomOp.forward_native for SiluAndMul and QuantFP8 to avoid raw torch ops inside opaque custom ops (#32806)

2026-01-22 19:52:26 -08:00

parameter.py

[Docs] Replace rst style double-backtick with md single-backtick (#27091)

2025-10-17 02:47:34 -07:00

utils.py

[Platform] Deprecate seed_everything (#31659)

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