[None][feat] Muse Spark Open modeling_v2 TEP target: GB300 and Vera Rubin fast paths, and the DFlash 2 drafter transform on the sharded draft head - #21143

[None][feat] Muse Spark Open modeling_v2 TEP target: GB300 and Vera Rubin fast paths, and the DFlash 2 drafter transform on the sharded draft head#21143

xwang233 wants to merge 16 commits into

NVIDIA:feat/musespark-open-agentxNVIDIA/TensorRT-LLM:feat/musespark-open-agentxfrom

xwang233:mso-hcv3midc/agentx-tepxwang233/TensorRT-LLM:mso-hcv3midc/agentx-tepCopy head branch name to clipboard