slaren 87e397d00b

ggml : fix quant dot product with odd number of blocks (#8549) ...

* ggml : fix iq4_nl dot product with odd number of blocks

* ggml : fix odd blocks for ARM_NEON (#8556)

* ggml : fix iq4_nl dot product with odd number of blocks

* ggml : fix q4_1

* ggml : fix q5_0

* ggml : fix q5_1

* ggml : fix iq4_nl metal

ggml-ci

* ggml : fix q4_0

* ggml : fix q8_0

ggml-ci

* ggml : remove special Q4_0 code for first 2 blocks

* ggml : fix sumf redefinition

---------

Co-authored-by: slaren <slarengh@gmail.com>

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

2024-07-19 17:17:27 +02:00

..

ggml-cann

[CANN] Add Ascend NPU backend (#6035)

2024-07-17 14:23:50 +03:00

ggml-cuda

cuda : suppress 'noreturn' warn in no_device_code (#8414)

2024-07-11 17:53:42 +02:00

ggml-sycl

[SYCL] add concat through dim 1/2 (#8483)

2024-07-15 19:32:15 +08:00

kompute @ 4565194ed7

llama : reorganize source code + improve CMake (#8006)

2024-06-26 18:33:02 +03:00

kompute-shaders

llama : reorganize source code + improve CMake (#8006)

2024-06-26 18:33:02 +03:00

llamafile

ggml : move sgemm sources to llamafile subfolder (#8394)

2024-07-10 15:23:29 +03:00

vulkan-shaders

Vulkan MMQ Fix (#8479)

2024-07-15 09:38:52 +02:00

CMakeLists.txt

[CANN] Add Ascend NPU backend (#6035)

2024-07-17 14:23:50 +03:00

ggml-aarch64.c

ggml : suppress unknown pragma 'GCC' on windows (#8460)

2024-07-15 15:48:17 +03:00

ggml-aarch64.h

ggml : minor naming changes (#8433)

2024-07-12 10:46:02 +03:00

ggml-alloc.c

CUDA: fix partial offloading for ne0 % 256 != 0 (#8572)

2024-07-18 23:48:47 +02:00

ggml-backend-impl.h

llama : reorganize source code + improve CMake (#8006)

2024-06-26 18:33:02 +03:00

ggml-backend.c

CUDA: fix partial offloading for ne0 % 256 != 0 (#8572)

2024-07-18 23:48:47 +02:00

ggml-blas.cpp

ggml : add NVPL BLAS support (#8329) (#8425)

2024-07-11 18:49:15 +02:00

ggml-cann.cpp

[CANN] Add Ascend NPU backend (#6035)

2024-07-17 14:23:50 +03:00

ggml-common.h

ggml : add AArch64 optimized GEMV and GEMM Q4 kernels (#5780)

2024-07-10 15:14:51 +03:00

ggml-cuda.cu

CUDA: fix partial offloading for ne0 % 256 != 0 (#8572)

2024-07-18 23:48:47 +02:00

ggml-impl.h

ggml : add AArch64 optimized GEMV and GEMM Q4 kernels (#5780)

2024-07-10 15:14:51 +03:00

ggml-kompute.cpp

llama : reorganize source code + improve CMake (#8006)

2024-06-26 18:33:02 +03:00

ggml-metal.m

ggml : fix quant dot product with odd number of blocks (#8549)

2024-07-19 17:17:27 +02:00

ggml-metal.metal

ggml : fix quant dot product with odd number of blocks (#8549)

2024-07-19 17:17:27 +02:00

ggml-quants.c

ggml : fix quant dot product with odd number of blocks (#8549)

2024-07-19 17:17:27 +02:00

ggml-quants.h

ggml : minor naming changes (#8433)

2024-07-12 10:46:02 +03:00

ggml-rpc.cpp

llama : reorganize source code + improve CMake (#8006)

2024-06-26 18:33:02 +03:00

ggml-sycl.cpp

[SYCL] add concat through dim 1/2 (#8483)

2024-07-15 19:32:15 +08:00

ggml-vulkan.cpp

Vulkan MMQ Fix (#8479)

2024-07-15 09:38:52 +02:00

ggml.c

ggml : add friendlier error message to fopen errors (#8575)

2024-07-19 14:05:45 +03:00