4 Commits

Author	SHA1	Message	Date
leejet	275ab58e01	perf: reduce CPU overhead in graph execution and sampling (#1997)	2026-09-19 18:32:58 +08:00
leejet	3e037a81e4	perf: accelerate VAE direct 3D convolutions (#1996)	2026-09-19 17:50:01 +08:00
leejet	7f410a3793	feat: add linear and attention scale overrides (#1964)	2026-09-12 01:41:28 +08:00
leejet	31ab2b2e08	refactor: split ggml extensions and move implementations to cpp files (#1945)	2026-09-07 23:34:45 +08:00