Spaces:

Duplicated from natasa365/whisper.cpp

Xenobd
/

whisper.cpp

Running

App Files Files Community

whisper.cpp / ggml /src

8.72 MB

100 contributors

History: 1149 commits

Reese Levine

ggml: Add initial WebGPU backend (llama/14521)

4b3da1d 4 months ago

ggml-amx
ggml : adapt AMX to tensor->grad removal (llama/0) about 1 year ago
ggml-blas
ggml : fix field name when new ggml_backend (llama/14944) 4 months ago
ggml-cann
CANN: GGML_OP_CPY optimization (llama/15070) 4 months ago
ggml-cpu
ggml: initial IBM zDNN backend (llama/14975) 4 months ago
ggml-cuda
CUDA: fix negative KV_max values in FA (llama/15321) 4 months ago
ggml-hip
HIP: bump requirement to rocm 6.1 (llama/15296) 4 months ago
ggml-metal
llama : add gpt-oss (llama/15091) 4 months ago
ggml-musa
musa: upgrade musa sdk to rc4.2.0 (llama/14498) 5 months ago
ggml-opencl
OpenCL: add initial FA support (llama/14987) 4 months ago
ggml-rpc
ggml-rpc: chunk send()/recv() to avoid EINVAL for very large tensors over RPC (macOS & others) (llama/15188) 4 months ago
ggml-sycl
sycl: Fix and disable more configurations of mul_mat (llama/15151) 4 months ago
ggml-vulkan
vulkan: disable spirv-opt for bfloat16 shaders (llama/15352) 4 months ago
ggml-webgpu
ggml: Add initial WebGPU backend (llama/14521) 4 months ago
ggml-zdnn
ggml : initial zDNN backend (llama/14975) 4 months ago
CMakeLists.txt

15.4 kB

ggml: initial IBM zDNN backend (llama/14975) 4 months ago
ggml-alloc.c

38.2 kB

llama : add gpt-oss (llama/15091) 4 months ago
ggml-backend-impl.h

12 kB

ggml : upgrade init_tensor API to return a ggml_status (llama/11854) 10 months ago
ggml-backend-reg.cpp

17.7 kB

ggml: initial IBM zDNN backend (llama/14975) 4 months ago
ggml-backend.cpp

79.2 kB

ggml : fix fallback to CPU for ununsupported ops (llama/15118) 4 months ago
ggml-common.h

134 kB

llama : add gpt-oss (llama/15091) 4 months ago
ggml-impl.h

20.2 kB

llama : add gpt-oss (llama/15091) 4 months ago
ggml-opt.cpp

42 kB

finetune: SGD optimizer, more CLI args (llama/13873) 4 months ago
ggml-quants.c

217 kB

ggml-quants : fix make_qp_quants NANs and IQ1 assertion errors (llama/15379) 4 months ago
ggml-quants.h

8.71 kB

llama : add gpt-oss (llama/15091) 4 months ago
ggml-threading.cpp

250 Bytes

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

198 Bytes

remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (llama/10797) about 1 year ago
ggml.c

225 kB

ggml: fix ggml_conv_1d_dw bug (ggml/1323) 4 months ago
ggml.cpp

738 Bytes

ggml : Print backtrace on uncaught C++ exceptions (ggml/1232) 7 months ago
gguf.cpp

46.4 kB

ggml : prevent integer overflow in gguf tensor size calculation (llama/14595) 5 months ago