Yongye ZhuandClaude Opus 5.5 378504a544 [MoE] Defer the TRTLLM-Gen top-k finalize on the modular path (#58635) ...

Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>

2026-09-25 15:38:29 +08:00

..

schemes

[MoE] Defer the TRTLLM-Gen top-k finalize on the modular path (#58635)

2026-09-25 15:38:29 +08:00

__init__.py

[quant][autoround]Refactor INC quantization into package with INCScheme orchestrator (#40601)

2026-06-17 21:51:32 +08:00

config_parser.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

inc_linear.py

[quant][autoround]Refactor INC quantization into package with INCScheme orchestrator (#40601)

2026-06-17 21:51:32 +08:00

inc.py

add 2/3/5/6/7 CUDA support in AutoRound format (#52890)

2026-09-07 09:59:19 +08:00