public_git
/
whisper.cpp
mirror of https://github.com/ggml-org/whisper.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
whisper.cpp/ggml/src
History
amritahs-ibm 124eec1664 llamafile : ppc64le MMA INT8 implementation (llama/10912) 
This change upstreams llamafile's cpu matrix
multiplication kernels for ppc64le using MMA
builtins for quantised int8 datatype.

This change results in 10% - 70% improvement
in total speed(ie all tokens/total time), across
various batch sizes.

The patch is tested with Meta-Lllama-3-8B,
Mistral-7B, Llama-2-7B-chat-hf models on a
IBM POWER10 machine.

Signed-off-by: Amrita H S <amritahs@linux.vnet.ibm.com>
 		2025-01-14 10:38:01 +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 llama : add Qwen2VL support + multimodal RoPE (llama/10361) 2024-12-18 12:52:16 +02:00
ggml-cpu llamafile : ppc64le MMA INT8 implementation (llama/10912) 2025-01-14 10:38:01 +02:00
ggml-cuda CUDA: add BF16 support (llama/11093) 2025-01-14 10:38:01 +02:00
ggml-hip ggml : add support for dynamic loading of backends (llama/10469) 2024-12-08 20:14:35 +02:00
ggml-kompute llama : add Qwen2VL support + multimodal RoPE (llama/10361) 2024-12-18 12:52:16 +02:00
ggml-metal ggml : do not install metal source when embed library (ggml/1054) 2025-01-04 10:45:01 +02:00
ggml-musa ggml : remove old files (skip) (#0) 2024-12-08 23:04:26 +02:00
ggml-rpc rpc : code cleanup (llama/11107) 2025-01-14 10:38:01 +02:00
ggml-sycl SYCL: Use get_multi_ptr instead of deprecated get_pointer in wkv6 (llama/11087) 2025-01-14 10:38:01 +02:00
ggml-vulkan Disable GL_KHR_cooperative_matrix Vulkan extension if not available. (llama/11117) 2025-01-14 10:38:01 +02:00
CMakeLists.txt GGUF: C++ refactor, backend support, misc fixes (llama/11030) 2025-01-14 10:38:01 +02:00
ggml-alloc.c ggml : remove return from ggml_gallocr_allocate_node (ggml/1048) 2024-12-18 12:52:16 +02:00
ggml-backend-impl.h ggml : move AMX to the CPU backend (llama/10570) 2024-12-08 20:14:35 +02:00
ggml-backend-reg.cpp ggml : allow loading backend with env variable (ggml/1059) 2025-01-14 10:38:01 +02:00
ggml-backend.cpp ggml-backend : only offload from host buffers (fix) (llama/11124) 2025-01-14 10:38:01 +02:00
ggml-common.h CUDA: rename macros to avoid conflicts with WinAPI (llama/10736) 2024-12-18 12:52:16 +02:00
ggml-impl.h GGUF: C++ refactor, backend support, misc fixes (llama/11030) 2025-01-14 10:38:01 +02:00
ggml-opt.cpp ggml-opt: fix data corruption (ggml/1022) 2024-12-08 20:14:35 +02:00
ggml-quants.c ggml : refactor online repacking (llama/10446) 2024-12-18 12:52:16 +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 remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (llama/10797) 2024-12-18 12:52:16 +02:00
ggml.c GGUF: C++ refactor, backend support, misc fixes (llama/11030) 2025-01-14 10:38:01 +02:00