W

whisper.cpp

Settings | Report Duplicate

0

I Use This!

Very High Activity

Commits : Listings

Analyzed about 19 hours ago. based on code collected about 19 hours ago.

Commit Message	Contributor	Files Modified	Lines Added	Lines Removed	Code Location	Date
Jan 09, 2025 — Jan 09, 2026 Showing page 1 of 127 Search / Filter on:
ruby : fix segmentation fault (#3591)	KITAITI Makoto	More...				5 days ago
sync : ggml	Georgi Gerganov	More...				10 days ago
ggml : bump version to 0.9.5 (ggml/1410)	Georgi Gerganov	More...				10 days ago
talk-llama : sync llama.cpp	Georgi Gerganov	More...				10 days ago
sync : ggml	Georgi Gerganov	More...				10 days ago
metal : add count_equal op (llama/18314)	gatbontonpc	More...				10 days ago
CUDA: fix KQ max calculation (llama/18487)	Johannes Gäßler	More...				10 days ago
metal : remove BF16 x F16 kernels (llama/18456)	Georgi Gerganov	More...				10 days ago
sycl: add newline at the end of CMakeLists.txt (llama/18503)	Aman Gupta	More...				10 days ago
Work around broken IntelSYCLConfig.cmake in Intel oneAPI 2025.x (llama/18345)	Rahul Sathe	More...				11 days ago
kleidiai: add and integrate SVE 256-bit vector-length kernel (llama/18458)	Charles Xu	More...				11 days ago
CUDA: add log line when mxfp4 acceleration is used (llama/18483)	Aman Gupta	More...				11 days ago
CUDA: fix replacment of bad archs in CMake (llama/18457)	Johannes Gäßler	More...				12 days ago
CUDA: Blackwell features for non-native builds (llama/18436)	Johannes Gäßler	More...				12 days ago
cuda: fix race condition in cumsum (llama/18448)	Aman Gupta	More...				12 days ago
HIP: Use mmq on MFMA devices for MUL_MAT_ID in cases where a lot of splits would be generated (llama/18202)	uvos	More...				13 days ago
Revert "ggml-cuda: use CMAKE_CUDA_ARCHITECTURES if set when GGML_NATIVE=ON (#18413)" (llama/18426)	Aman Gupta	More...				13 days ago
rpc: fix segfault on invalid endpoint format (llama/18387)	o7si	More...				13 days ago
cmake: Added more x86_64 CPU backends when building with `GGML_CPU_ALL_VARIANTS=On` (llama/18186)	Boian Berberov	More...				13 days ago
ggml-cuda: use CMAKE_CUDA_ARCHITECTURES if set when GGML_NATIVE=ON (llama/18413)	QDelta	More...				14 days ago
opencl: allow resizing transpose buffers (llama/18384)	lhez	More...				14 days ago
ggml-cuda: Use same regex for GGML_NATIVE=OFF (llama/18407)	Aman Gupta	More...				14 days ago
vulkan: preprocess mul_mat_id experts and discard workgroups more quickly (llama/18352)	Jeff Bolz	More...				15 days ago
vulkan: optimize decodeFuncB in coopmat2 mul_mat_id shader (llama/18349)	Jeff Bolz	More...				15 days ago
vulkan: Use BK=32 for coopmat2 mul_mat_id (llama/18332)	Jeff Bolz	More...				15 days ago
vulkan: small dequantization improvements (llama/18380)	Eve	More...				15 days ago
vulkan: Support UPSCALE w/antialias (llama/18327)	Jeff Bolz	More...				15 days ago
vulkan: handle rope with large number of rows (llama/18306)	Jeff Bolz	More...				15 days ago
CANN: implement the SSM_CONV operator (llama/17737)	0Marble	More...				16 days ago
ggml-cuda: fix regex for arch list (llama/18371)	Aman Gupta	More...				16 days ago

←
1
2
3
4
5
6
7
8
9
…
126
127
→