Spaces:

natasa365
/

whisper.cpp

Sleeping

App Files Files Community

whisper.cpp / ggml /src

7.58 MB

Ctrl+K

Ctrl+K

100 contributors

History: 294 commits

ggerganov's picture

ggerganov HF Staff

ggml : adapt AMX to tensor->grad removal (llama/0)

8a67e9f over 1 year ago

ggml-amx
ggml : adapt AMX to tensor->grad removal (llama/0) over 1 year ago
ggml-blas
ggml : build backends as libraries (llama/10256) over 1 year ago
ggml-cann
ggml : build backends as libraries (llama/10256) over 1 year ago
ggml-cpu
llamafile : fix include path (llama/0) over 1 year ago
ggml-cuda
ggml: new optimization interface (ggml/988) over 1 year ago
ggml-hip
ggml : build backends as libraries (llama/10256) over 1 year ago
ggml-kompute
ggml : build backends as libraries (llama/10256) over 1 year ago
ggml-metal
ggml: new optimization interface (ggml/988) over 1 year ago
ggml-musa
ggml : build backends as libraries (llama/10256) over 1 year ago
ggml-rpc
ggml : build backends as libraries (llama/10256) over 1 year ago
ggml-sycl
sycl: Use syclcompat::dp4a (llama/10267) over 1 year ago
ggml-vulkan
vulkan: Optimize some mat-vec mul quant shaders (llama/10296) over 1 year ago
kompute-shaders
whisper : reorganize source code + improve CMake (#2256) almost 2 years ago
vulkan-shaders
vulkan: Optimize contiguous copies (llama/10254) over 1 year ago
CMakeLists.txt

9.48 kB
ggml: new optimization interface (ggml/988) over 1 year ago
ggml-aarch64.c

4.47 kB
ggml : optimize Q4_0 into Q4_0_X_Y repack (llama/10324) over 1 year ago
ggml-aarch64.h

642 Bytes
ggml : build backends as libraries (llama/10256) over 1 year ago
ggml-alloc.c

38.3 kB
ggml: new optimization interface (ggml/988) over 1 year ago
ggml-amx.cpp

14.3 kB
llama : refactor model loader with backend registry (llama/10026) over 1 year ago
ggml-backend-impl.h

10.1 kB
llama : refactor model loader with backend registry (llama/10026) over 1 year ago
ggml-backend-reg.cpp

4.84 kB
ggml : build backends as libraries (llama/10256) over 1 year ago
ggml-backend.cpp

98.3 kB
ggml: new optimization interface (ggml/988) over 1 year ago
ggml-blas.cpp

16.8 kB
llama : refactor model loader with backend registry (llama/10026) over 1 year ago
ggml-cann.cpp

75.9 kB
CANN: adjust backend registry refactor. (llama/10158) over 1 year ago
ggml-common.h

134 kB
ggml-quants : ternary packing for TriLMs and BitNet b1.58 (llama/8151) over 1 year ago
ggml-cpu-impl.h

15.9 kB
ggml : add ggml-cpu-impl.h (skip) (#0) over 1 year ago
ggml-cpu.c

471 kB
fix q4_0_8_8 format for corrupted tokens issue (llama/10198) over 1 year ago
ggml-cuda.cu

134 kB
metal : optimize FA kernels (llama/10171) over 1 year ago
ggml-impl.h

17.6 kB
ggml: new optimization interface (ggml/988) over 1 year ago
ggml-kompute.cpp

87.3 kB
kompute: add mul_mat_q4_k shader (llama/10097) over 1 year ago
ggml-metal.m

239 kB
metal : fix build and some more comments (llama/10229) over 1 year ago
ggml-metal.metal

270 kB
metal : more precise Q*K in FA vec kernel (llama/10247) over 1 year ago
ggml-opt.cpp

31.6 kB
ggml: new optimization interface (ggml/988) over 1 year ago
ggml-quants.c

214 kB
ggml : build backends as libraries (llama/10256) over 1 year ago
ggml-quants.h

8.34 kB
ggml : build backends as libraries (llama/10256) over 1 year ago
ggml-rpc.cpp

50.4 kB
ggml : move CPU backend to a separate file (llama/10144) over 1 year ago
ggml-sycl.cpp

186 kB
sycl : Fixes to broken builds and test-backend-ops (llama/10257) over 1 year ago
ggml-threading.cpp

250 Bytes
ggml : build backends as libraries (llama/10256) over 1 year ago
ggml-threading.h

161 Bytes
ggml : build backends as libraries (llama/10256) over 1 year ago
ggml-vulkan.cpp

429 kB
vulkan: Optimize contiguous copies (llama/10254) over 1 year ago
ggml.c

245 kB
ggml : fix compile warnings (llama/0) over 1 year ago
sgemm.cpp

31.6 kB
whisper : reorganize source code + improve CMake (#2256) almost 2 years ago
sgemm.h

302 Bytes
whisper : reorganize source code + improve CMake (#2256) almost 2 years ago