Spaces:

Duplicated from natasa365/whisper.cpp

Xenobd
/

whisper.cpp

Running

App Files Files Community

15 MB

100 contributors

History: 1141 commits

ggerganov's picture

ggml : fix UB in IQ2_S and IQ3_S (llama/6012)

0c552df unverified almost 2 years ago

.devops
docker : fix the publishing of the CUDA Docker image (#1704) almost 2 years ago
.github
whisper : add SYCL support (#1863) almost 2 years ago
bindings
bindings/go : add linker flags to make metal work (#1944) almost 2 years ago
cmake
cmake : update to 3.19 (#351) almost 3 years ago
coreml
coreml : fix ANE optimized encoder (#1716) almost 2 years ago
examples
talk-llama : use llama_decode instead of llama_eval almost 2 years ago
extra
extra : update sync scripts after ggml-common.h almost 2 years ago
grammars
whisper : add grammar-based sampling (#1229) about 2 years ago
models
openvino : fix convert-whisper-to-openvino.py (#1890) almost 2 years ago
openvino
whisper : replace `tensor->n_dims` with `ggml_n_dims(tensor)` (#1694) almost 2 years ago
samples
Create README.md about 3 years ago
spm-headers
swift : package no longer use ggml dependency (#1861) almost 2 years ago
tests
whisper : make large version explicit + fix data size units (#1493) about 2 years ago
.gitattributes

804 Bytes

Initial release about 3 years ago
.gitignore

803 Bytes

server : add a REST Whisper server example with OAI-like API (#1380) about 2 years ago
.gitmodules

96 Bytes

cmake : add submodule whisper.spm about 3 years ago
CMakeLists.txt

22.1 kB

cmake : add library versioning (#1352) almost 2 years ago
LICENSE

1.07 kB

license : update year (#739) over 2 years ago
Makefile

15.8 kB

make : fix CUBLAS link with WSL (#1878) almost 2 years ago
Package.swift

1.84 kB

swift : package no longer use ggml dependency (#1861) almost 2 years ago
README.md

39.2 kB

readme : recommend MacOS Sonoma for Core ML (#1917) almost 2 years ago
README_sycl.md

6.84 kB

whisper : add SYCL support (#1863) almost 2 years ago
ggml-alloc.c

36.6 kB

ggml : add ALiBi support for ggml_soft_max_ext (llama/5488) almost 2 years ago
ggml-alloc.h

2.93 kB

ggml-alloc : v3 (ggml/727) almost 2 years ago
ggml-backend-impl.h

5.96 kB

ggml : introduce ggml_status (ggml/750) almost 2 years ago
ggml-backend.c

67.4 kB

ggml : introduce ggml_status (ggml/750) almost 2 years ago
ggml-backend.h

11.6 kB

ggml : introduce ggml_status (ggml/750) almost 2 years ago
ggml-cuda.cu

444 kB

1.5 bit: we can do even better (llama/5999) almost 2 years ago
ggml-cuda.h

2.1 kB

ggml : introduce GGML_CALL function annotation (llama/4850) almost 2 years ago
ggml-impl.h

8.05 kB

ggml, ci : Windows ARM runner and build fixes (llama/5979) almost 2 years ago
ggml-kompute.cpp

79 kB

ggml : introduce ggml_status (ggml/750) almost 2 years ago
ggml-kompute.h

1.03 kB

src : relocate new backend sources almost 2 years ago
ggml-metal.h

2.32 kB

ggml-backend : sync remnant almost 2 years ago
ggml-metal.m

167 kB

metal : move mm_id indices to shared mem (llama/5982) almost 2 years ago
ggml-metal.metal

250 kB

1.5 bit: we can do even better (llama/5999) almost 2 years ago
ggml-opencl.cpp

85.8 kB

ggml : introduce ggml_status (ggml/750) almost 2 years ago
ggml-opencl.h

1.39 kB

Add OpenCL add kernel (llama/5151) almost 2 years ago
ggml-quants.c

499 kB

ggml : fix UB in IQ2_S and IQ3_S (llama/6012) almost 2 years ago
ggml-quants.h

19.4 kB

Better 1.5 bit quantization (llama/5971) almost 2 years ago
ggml-sycl.cpp

691 kB

sycl : update IQ1_S kernels (WIP - not working!) (llama/5995) almost 2 years ago
ggml-sycl.h

1.26 kB

Revert "[SYCL] fix error when set main gpu to non-zero (llama/5901)" (llama/5918) almost 2 years ago
ggml-vulkan.cpp

301 kB

ggml : remove old quantization functions (llama/5942) almost 2 years ago
ggml-vulkan.h

1.59 kB

Vulkan Improvements (llama/5835) almost 2 years ago
ggml.c

705 kB

ggml, ci : Windows ARM runner and build fixes (llama/5979) almost 2 years ago
ggml.h

87.7 kB

ggml : remove old quantization functions (llama/5942) almost 2 years ago
whisper.cpp

232 kB

whisper : document whisper_batch.n_seq_id (#1942) almost 2 years ago
whisper.h

30.1 kB

ggml : add abort_callback for cpu backend (ggml/725) almost 2 years ago