Kawrakow 1b05210904 IQ4_KSS improvements (#642) ...

* iq4_kss: slightly better quantization

* iq4_kss: CUDA MMQ

* iq4_kss: repack/convert to q8_k_r8 (AVX2)

* iq4_kss: repack/convert to q8_k_r8 (NEON)

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>

2025-07-23 20:50:57 +02:00

..

cmake

Merge vulkan code from mainline up to commit of 6/28/2025 (#563)

2025-07-02 08:49:42 +02:00

ggml-cann

Merge mainline - Aug 12 2024 (#17)

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

ggml-cuda

IQ4_KSS improvements (#642)

2025-07-23 20:50:57 +02:00

ggml-sycl

Merge mainline - Aug 12 2024 (#17)

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

iqk

IQ4_KSS improvements (#642)

2025-07-23 20:50:57 +02:00

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

Vulkan: a fresh start (#608)

2025-07-15 08:03:13 +02:00

CMakeLists.txt

Add GGML_MAX_CONTEXTS definition in CMakeLists.txt (#622)

2025-07-17 08:50:42 +02:00

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 vulkan code from mainline up to commit of 6/28/2025 (#563)

2025-07-02 08:49:42 +02:00

ggml-backend-impl.h

Merge vulkan code from mainline up to commit of 6/28/2025 (#563)

2025-07-02 08:49:42 +02:00

ggml-backend.c

Fix debug build failure with RPC off (#579)

2025-07-03 15:26:28 +02:00

ggml-blas.cpp

Merge mainline - Aug 12 2024 (#17)

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

ggml-cann.cpp

Merge vulkan code from mainline up to commit of 6/28/2025 (#563)

2025-07-02 08:49:42 +02:00

ggml-common.h

Adding IQ1_KT - 1.75 bpw SOTA quants (#616)

2025-07-20 10:05:23 +02:00

ggml-cuda.cu

Adding IQ1_KT - 1.75 bpw SOTA quants (#616)

2025-07-20 10:05:23 +02:00

ggml-impl.h

Vulkan: a fresh start (#608)

2025-07-15 08:03:13 +02:00

ggml-kompute.cpp

Merge vulkan code from mainline up to commit of 6/28/2025 (#563)

2025-07-02 08:49:42 +02:00

ggml-metal.m

Adding IQ2_KL (#602)

2025-07-14 18:55:08 +02:00

ggml-metal.metal

Adding IQ2_KL (#602)

2025-07-14 18:55:08 +02:00

ggml-quants.c

Adding IQ1_KT - 1.75 bpw SOTA quants (#616)

2025-07-20 10:05:23 +02:00

ggml-quants.h

IQ1_M_R4: better 1.75 bpw quants (#187)

2025-02-06 14:08:52 +02:00

ggml-rpc.cpp

Merge vulkan code from mainline up to commit of 6/28/2025 (#563)

2025-07-02 08:49:42 +02:00

ggml-sycl.cpp

Merge vulkan code from mainline up to commit of 6/28/2025 (#563)

2025-07-02 08:49:42 +02:00

ggml-vulkan.cpp

Vulkan: a fresh start (#608)

2025-07-15 08:03:13 +02:00

ggml.c

Adding IQ1_KT - 1.75 bpw SOTA quants (#616)

2025-07-20 10:05:23 +02:00