Spaces:

Duplicated from natasa365/whisper.cpp

Xenobd
/

whisper.cpp

Running

App Files Files Community

whisper.cpp / ggml /include

152 kB

100 contributors

History: 102 commits

JohannesGaessler's picture

JohannesGaessler

llama/ggml: add LLM training support (llama/10544)

8d3b3c1 7 months ago

ggml-alloc.h

3.01 kB

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

20 kB

Add `--no-op-offload` to improve `-ot` pp perf in MoE models like llama4 400B (llama/13386) 7 months ago
ggml-blas.h

586 Bytes

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

4.55 kB

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

1.65 kB

ggml : fix ggml_gallocr_ptr type (ggml/1205) 8 months ago
ggml-cpu.h

7.26 kB

ggml: move fp16/bf16 conversion optimizations to CPU backend + export conversion APIs (llama/13107) 8 months ago
ggml-cuda.h

1.59 kB

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

1.16 kB

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

2.44 kB

repo : update links to new url (llama/11886) 10 months ago
ggml-opencl.h

581 Bytes

Introducing experimental OpenCL backend with support for Qualcomm Adreno GPUs (llama/10693) about 1 year ago
ggml-opt.h

13.2 kB

llama/ggml: add LLM training support (llama/10544) 7 months ago
ggml-rpc.h

1.07 kB

rpc : do not wait for response when sending RPC_CMD_SET_TENSOR (llama/12943) 8 months ago
ggml-sycl.h

1.76 kB

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

952 Bytes

vulkan: Make Vulkan optional at runtime (ggml/11493). (llama/11494) 11 months ago
ggml.h

82.2 kB

llama/ggml: add LLM training support (llama/10544) 7 months ago
gguf.h

10.2 kB

GGUF: C++ refactor, backend support, misc fixes (skip) (llama/11030) 11 months ago