Georgi Gerganov 4d73962da4 metal : small-batch mat-mul kernels (llama/10581) ... * metal : small-batch mat-mul kernels ggml-ci * metal : add rest of types ggml-ci * metal : final adjustments ggml-ci * metal : add comments ggml-ci		2024-12-08 20:14:35 +02:00
..
ggml-amx	ggml : adapt AMX to tensor->grad removal (llama/0)	2024-11-20 21:00:08 +02:00
ggml-blas	ggml : add support for dynamic loading of backends (llama/10469)	2024-12-08 20:14:35 +02:00
ggml-cann	CANN: RoPE operator optimization (llama/10563)	2024-12-08 20:14:35 +02:00
ggml-cpu	ggml-cpu: replace AArch64 NEON assembly with intrinsics in ggml_gemv_q4_0_4x4_q8_0() (llama/10567)	2024-12-08 20:14:35 +02:00
ggml-cuda	Add some minimal optimizations for CDNA (llama/10498)	2024-12-08 20:14:35 +02:00
ggml-hip	ggml : add support for dynamic loading of backends (llama/10469)	2024-12-08 20:14:35 +02:00
ggml-kompute	kompute : improve backend to pass test_backend_ops (llama/10542)	2024-12-08 20:14:35 +02:00
ggml-metal	metal : small-batch mat-mul kernels (llama/10581)	2024-12-08 20:14:35 +02:00
ggml-musa	mtgpu: Add MUSA_DOCKER_ARCH in Dockerfiles && update cmake and make (llama/10516)	2024-12-08 20:14:35 +02:00
ggml-rpc	ggml : add support for dynamic loading of backends (llama/10469)	2024-12-08 20:14:35 +02:00
ggml-sycl	SYCL: Fix and switch to GGML_LOG system instead of fprintf (llama/10579)	2024-12-08 20:14:35 +02:00
ggml-vulkan	vulkan: Dynamic subgroup size support for Q6_K mat_vec (llama/10536)	2024-12-08 20:14:35 +02:00
CMakeLists.txt	cmake : enable warnings in llama (llama/10474)	2024-12-08 20:14:35 +02:00
ggml-aarch64.c	ggml : optimize Q4_0 into Q4_0_X_Y repack (llama/10324)	2024-11-20 21:00:08 +02:00
ggml-aarch64.h	ggml : build backends as libraries (llama/10256)	2024-11-20 21:00:08 +02:00
ggml-alloc.c	ggml: new optimization interface (ggml/988)	2024-11-20 21:00:08 +02:00
ggml-backend-impl.h	ggml : add support for dynamic loading of backends (llama/10469)	2024-12-08 20:14:35 +02:00
ggml-backend-reg.cpp	llama : accept a list of devices to use to offload a model (llama/10497)	2024-12-08 20:14:35 +02:00
ggml-backend.cpp	ggml-opt: fix data corruption (ggml/1022)	2024-12-08 20:14:35 +02:00
ggml-common.h	ggml-cpu: support IQ4_NL_4_4 by runtime repack (llama/10541)	2024-12-08 20:14:35 +02:00
ggml-impl.h	Do not include arm_neon.h when compiling CUDA code (ggml/1028)	2024-12-08 20:14:35 +02:00
ggml-opt.cpp	ggml-opt: fix data corruption (ggml/1022)	2024-12-08 20:14:35 +02:00
ggml-quants.c	ggml : build backends as libraries (llama/10256)	2024-11-20 21:00:08 +02:00
ggml-quants.h	ggml : build backends as libraries (llama/10256)	2024-11-20 21:00:08 +02:00
ggml-threading.cpp	ggml : build backends as libraries (llama/10256)	2024-11-20 21:00:08 +02:00
ggml-threading.h	ggml : build backends as libraries (llama/10256)	2024-11-20 21:00:08 +02:00
ggml.c	ggml-cpu: support IQ4_NL_4_4 by runtime repack (llama/10541)	2024-12-08 20:14:35 +02:00