Spaces:

Duplicated from natasa365/whisper.cpp

Xenobd
/

whisper.cpp

Sleeping

App Files Files Community

whisper.cpp / ggml /src

7.43 MB

Ctrl+K

Ctrl+K

100 contributors

History: 808 commits

Yibo Cai

arm64: optimize q6_k_q8_k kernel with i8mm (llama/13519)

03048ea over 1 year ago

ggml-amx
ggml : adapt AMX to tensor->grad removal (llama/0) almost 2 years ago
ggml-blas
ggml : add support for dynamic loading of backends (llama/10469) almost 2 years ago
ggml-cann
CANN: Add support for async operator submission (llama/12864) over 1 year ago
ggml-cpu
arm64: optimize q6_k_q8_k kernel with i8mm (llama/13519) over 1 year ago
ggml-cuda
CUDA: fix crash on large batch size for quant. MoE (llama/13537) over 1 year ago
ggml-hip
CUDA/HIP: Share the same unified memory allocation logic. (llama/12934) over 1 year ago
ggml-kompute
llama : add Qwen2VL support + multimodal RoPE (llama/10361) almost 2 years ago
ggml-metal
metal : use FA-vec kernel up to batch size 20 (llama/13496) over 1 year ago
ggml-musa
cuda : enable CUDA Graph on CUDA Toolkit < 12.x (llama/12394) over 1 year ago
ggml-opencl
opencl: remove unnecessary assert for `add` (llama/13257) over 1 year ago
ggml-rpc
rpc : add rpc_msg_set_tensor_hash_req (llama/13353) over 1 year ago
ggml-sycl
enable dpcpp nightly builds with libraries (llama/13406) over 1 year ago
ggml-vulkan
cmake: simplify vulkan shader test logic (llama/13263) over 1 year ago
CMakeLists.txt

11.6 kB
cmake : removed stdc++fs (#3097) over 1 year ago
ggml-alloc.c

38.5 kB
ggml: Don't assert fail when tensor data changes (llama/13222) over 1 year ago
ggml-backend-impl.h

12 kB
ggml : upgrade init_tensor API to return a ggml_status (llama/11854) over 1 year ago
ggml-backend-reg.cpp

17.4 kB
ggml-backend : fix backend search path (llama/12330) over 1 year ago
ggml-backend.cpp

77.8 kB
llama/ggml: add LLM training support (llama/10544) over 1 year ago
ggml-common.h

133 kB
musa: fix all warnings, re-enable `-DLLAMA_FATAL_WARNINGS=ON` in ci and update doc (llama/12611) over 1 year ago
ggml-impl.h

19.4 kB
ggml-impl.h: fix build on POWER9 (llama/12855) over 1 year ago
ggml-opt.cpp

39.8 kB
mnist: fix segmentation fault (ggml/1227) over 1 year ago
ggml-quants.c

215 kB
whisper: remove MSVC warnings pragmas (#3090) over 1 year ago
ggml-quants.h

8.34 kB
ggml : build backends as libraries (llama/10256) almost 2 years ago
ggml-threading.cpp

250 Bytes
ggml : build backends as libraries (llama/10256) almost 2 years ago
ggml-threading.h

198 Bytes
remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (llama/10797) almost 2 years ago
ggml.c
209 kB
ggml : fix apple OS check in ggml_print_backtrace (ggml/1229) over 1 year ago
gguf.cpp

45.1 kB
Fix clang warning in gguf_check_reserved_keys (llama/12686) over 1 year ago