4 Commits

Author	SHA1	Message	Date
Jeff Bolz	c44d449635	vulkan: fuse adds (llama/15252) ... * vulkan: fuse adds Fuse adds that have the same shape, which are common in MoE models. It will currently fuse up to 6 adds, because we assume no more than 8 descriptors per dispatch. But this could be changed. * check runtimeDescriptorArray feature * disable multi_add for Intel due to likely driver bug	2025-08-18 20:30:45 +03:00
Jeff Bolz	b33841c453	vulkan: add RTE variants for glu/add/sub/mul/div (llama/14653)	2025-07-20 00:23:50 +03:00
Jeff Bolz	fc84ecd445	vulkan: Use push constant offset to handle misaligned descriptors (llama/10987)	2025-01-04 10:45:01 +02:00
Diego Devesa	746bf2596f	ggml : build backends as libraries (llama/10256) ... * ggml : build backends as libraries --------- Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> Co-authored-by: R0CKSTAR <xiaodong.ye@mthreads.com>	2024-11-20 21:00:08 +02:00