Spaces:

Duplicated from natasa365/whisper.cpp

Xenobd
/

whisper.cpp

Running

App Files Files Community

whisper.cpp / ggml /src

5.27 MB

100 contributors

History: 231 commits

mingfeima's picture

ggml : add AMX backend (llama/8998)

1152a79 about 1 year ago

ggml-amx
ggml : add AMX backend (llama/8998) about 1 year ago
ggml-cann
cann: fix crash when llama-bench is running on multiple cann devices (llama/9627) about 1 year ago
ggml-cuda
CUDA: fix MMQ for non-contiguous src0, add tests (llama/10021) about 1 year ago
ggml-sycl
fix mul_mat_vec_q and *_vec_q error (llama/9939) about 1 year ago
kompute-shaders
whisper : reorganize source code + improve CMake (#2256) over 1 year ago
vulkan-shaders
vulkan : argsort barriers must be under uniform control flow (ggml/951) about 1 year ago
CMakeLists.txt

54.7 kB

add amx kernel for gemm (llama/8998) about 1 year ago
ggml-aarch64.c

193 kB

ggml : add run-time detection of neon, i8mm and sve (llama/9331) about 1 year ago
ggml-aarch64.h

2.01 kB

ggml : add ggml-aarch64 (ggml/0) over 1 year ago
ggml-alloc.c

38.4 kB

ggml : move more prints to the ggml log system (llama/9839) about 1 year ago
ggml-amx.cpp

14.8 kB

ggml : add AMX backend (llama/8998) about 1 year ago
ggml-backend-impl.h

10.8 kB

ggml : add backend registry / device interfaces to BLAS backend (llama/9752) about 1 year ago
ggml-backend.cpp

97.4 kB

Adapt to dynamically loadable backends mechanism (llama/9970) about 1 year ago
ggml-blas.cpp

17.2 kB

ggml : move more prints to the ggml log system (llama/9839) about 1 year ago
ggml-cann.cpp

77.3 kB

Adapt to dynamically loadable backends mechanism (llama/9970) about 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) about 1 year ago
ggml-cuda.cu

134 kB

CUDA: fix insufficient buffer clearing for MMQ (llama/10032) about 1 year ago
ggml-impl.h

6.47 kB

fix: use `vm_allocate` to allocate CPU backend buffer on macOS (llama/9875) about 1 year ago
ggml-kompute.cpp

80.2 kB

ggml-backend : add device and backend reg interfaces (llama/9707) about 1 year ago
ggml-metal.m

210 kB

metal : support permuted matrix multiplicaions (llama/10033) about 1 year ago
ggml-metal.metal

247 kB

metal : support permuted matrix multiplicaions (llama/10033) about 1 year ago
ggml-quants.c

693 kB

ggml : add run-time detection of neon, i8mm and sve (llama/9331) about 1 year ago
ggml-quants.h

12.9 kB

ggml : add run-time detection of neon, i8mm and sve (llama/9331) about 1 year ago
ggml-rpc.cpp

51.5 kB

rpc : pack only RPC structs (llama/9959) about 1 year ago
ggml-sycl.cpp

220 kB

Add SYCL Backend registry, device and Event Interfaces (llama/9705) about 1 year ago
ggml-vulkan.cpp

425 kB

vulkan : add backend registry / device interfaces (llama/9721) about 1 year ago
ggml.c

783 kB

CUDA: fix MMQ for non-contiguous src0, add tests (llama/10021) about 1 year ago
sgemm.cpp

31.6 kB

whisper : reorganize source code + improve CMake (#2256) over 1 year ago
sgemm.h

302 Bytes

whisper : reorganize source code + improve CMake (#2256) over 1 year ago