Skip to content

[cuda] GGUF Q6_K real packed INT6 (W6A8 dp4a) + GGUF CI export#20229

Draft
Gasoonjia wants to merge 4 commits into
g4-opt-prefill-window-sdpafrom
g4-int6-gguf
Draft

[cuda] GGUF Q6_K real packed INT6 (W6A8 dp4a) + GGUF CI export#20229
Gasoonjia wants to merge 4 commits into
g4-opt-prefill-window-sdpafrom
g4-int6-gguf

Commits

Commits on Jun 12, 2026