3 people f38c6778ce [quantization] Add per-token NVFP4 quantization MoE support for ReLU2 (#56740) ...

Signed-off-by: Xuanteng Huang <xuantengh@nvidia.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>

2026-10-07 22:01:09 +00:00

..

__init__.py

[Fast Start] Cache the MTP draft model in a separate daemon group (#57312)

2026-09-22 03:13:38 +00:00

daemon.py

[Fast Start] Charge daemon-held weights against gpu_memory_utilization (#57298)

2026-09-29 17:58:35 +00:00

ipc_loader.py

[Fast Start] Charge daemon-held weights against gpu_memory_utilization (#57298)

2026-09-29 17:58:35 +00:00

protocol.py

[quantization] Add per-token NVFP4 quantization MoE support for ReLU2 (#56740)

2026-10-07 22:01:09 +00:00

utils.py

[Fast Start] Cache the MTP draft model in a separate daemon group (#57312)

2026-09-22 03:13:38 +00:00