Iwan Kawrakow 86237d0555 POC: per row scale ...

This is a POC how to work around opinionated ggml to
have scales per row rather than per block.
Only implemened for Zen4 and only for iq2_tn.

2024-09-25 13:10:33 +03:00

..

ggml-cann

Merge mainline - Aug 12 2024 (#17)

2024-08-12 15:14:32 +02:00

ggml-cuda

Adding bf16 support to CUDA (#40)

2024-09-14 20:02:32 +03:00

ggml-sycl

Merge mainline - Aug 12 2024 (#17)

2024-08-12 15:14:32 +02:00

iqk

POC: per row scale

2024-09-25 13:10:33 +03:00

kompute @ 4565194ed7

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

kompute-shaders

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

llamafile

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

vulkan-shaders

Merge mainline - Aug 12 2024 (#17)

2024-08-12 15:14:32 +02:00

CMakeLists.txt

Fix compiler warnings (#58)

2024-09-17 14:31:29 +03:00

ggml-aarch64.c

Merge mainline - Aug 12 2024 (#17)

2024-08-12 15:14:32 +02:00

ggml-aarch64.h

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

ggml-alloc.c

Merge mainline - Aug 12 2024 (#17)

2024-08-12 15:14:32 +02:00

ggml-backend-impl.h

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

ggml-backend.c

Merge mainline - Aug 12 2024 (#17)

2024-08-12 15:14:32 +02:00

ggml-blas.cpp

Merge mainline - Aug 12 2024 (#17)

2024-08-12 15:14:32 +02:00

ggml-cann.cpp

Merge mainline - Aug 12 2024 (#17)

2024-08-12 15:14:32 +02:00

ggml-common.h

POC: per row scale

2024-09-25 13:10:33 +03:00

ggml-cuda.cu

Adding bf16 support to CUDA (#40)

2024-09-14 20:02:32 +03:00

ggml-impl.h

Merge mainline - Aug 12 2024 (#17)

2024-08-12 15:14:32 +02:00

ggml-kompute.cpp

Merge mainline - Aug 12 2024 (#17)

2024-08-12 15:14:32 +02:00

ggml-metal.m

BF16 support on Metal (#56)

2024-09-17 10:54:42 +03:00

ggml-metal.metal

Use fp32 for K*Q in Metal FA implementation (#62)

2024-09-25 13:08:55 +03:00

ggml-quants.c

POC: per row scale

2024-09-25 13:10:33 +03:00

ggml-quants.h

Merge mainline - Aug 12 2024 (#17)

2024-08-12 15:14:32 +02:00

ggml-rpc.cpp

Merge mainline - Aug 12 2024 (#17)

2024-08-12 15:14:32 +02:00

ggml-sycl.cpp

Merge mainline - Aug 12 2024 (#17)

2024-08-12 15:14:32 +02:00

ggml-vulkan.cpp

Merge mainline - Aug 12 2024 (#17)

2024-08-12 15:14:32 +02:00

ggml.c

POC: per row scale

2024-09-25 13:10:33 +03:00