Georgi Gerganov f221d56220 ggml : alloc ggml_contexts on the heap (whisper/2525)

2024-11-01 10:24:50 +02:00

..

ggml-amx

…

ggml-cann

…

ggml-cuda

increase cuda_cpy block size (ggml/996)

2024-10-26 10:33:56 +03:00

ggml-sycl

…

kompute @ 4565194ed7

…

kompute-shaders

kompute: add mul_mat_q4_k shader (#10097)

2024-10-31 11:09:52 +02:00

llamafile

llamafile : extend sgemm.cpp support for Q5_0 models (#10010)

2024-10-25 10:27:41 +03:00

vulkan-shaders

ggml: Add POOL2D OP for GPU acceleration to the Vulkan backend in the MobileVLM model. (#9763)

2024-10-29 09:52:56 +01:00

CMakeLists.txt

build: fix build error in Windows env with OneAPI setup (#10107)

2024-11-01 11:09:59 +08:00

ggml-aarch64.c

ggml : add Q4_0_8_8 RISC-V GEMV and GEMM kernels (#10029)

2024-10-30 09:00:40 +02:00

ggml-aarch64.h

…

ggml-alloc.c

…

ggml-amx.cpp

llama : refactor model loader with backend registry (#10026)

2024-10-30 02:01:23 +01:00

ggml-backend-impl.h

llama : refactor model loader with backend registry (#10026)

2024-10-30 02:01:23 +01:00

ggml-backend.cpp

llama : fix buffer checks for mamba and rwk (#10111)

2024-10-31 22:54:23 +01:00

ggml-blas.cpp

llama : refactor model loader with backend registry (#10026)

2024-10-30 02:01:23 +01:00

ggml-cann.cpp

llama : refactor model loader with backend registry (#10026)

2024-10-30 02:01:23 +01:00

ggml-common.h

…

ggml-cpu-impl.h

…

ggml-cuda.cu

llama : fix buffer checks for mamba and rwk (#10111)

2024-10-31 22:54:23 +01:00

ggml-impl.h

…

ggml-kompute.cpp

kompute: add mul_mat_q4_k shader (#10097)

2024-10-31 11:09:52 +02:00

ggml-metal.m

llama : refactor model loader with backend registry (#10026)

2024-10-30 02:01:23 +01:00

ggml-metal.metal

metal : support permuted matrix multiplicaions (#10033)

2024-10-25 22:26:15 +03:00

ggml-quants.c

…

ggml-quants.h

…

ggml-rpc.cpp

llama : refactor model loader with backend registry (#10026)

2024-10-30 02:01:23 +01:00

ggml-sycl.cpp

llama : refactor model loader with backend registry (#10026)

2024-10-30 02:01:23 +01:00

ggml-vulkan.cpp

llama : refactor model loader with backend registry (#10026)

2024-10-30 02:01:23 +01:00

ggml.c

ggml : alloc ggml_contexts on the heap (whisper/2525)

2024-11-01 10:24:50 +02:00