W

whisper.cpp

Settings | Report Duplicate

0

I Use This!

Very High Activity

Commits : Listings

Analyzed 1 day ago. based on code collected 1 day ago.

Commit Message	Contributor	Files Modified	Lines Added	Lines Removed	Code Location	Date
Jun 25, 2024 — Jun 25, 2025 Showing page 24 of 94 Search / Filter on:
CUDA: fix Volta FlashAttention logic (llama/11615)	Johannes Gäßler	More...				5 months ago
HIP: fix flash_attn_stream_k_fixup warning (llama/11604)	Johannes Gäßler	More...				5 months ago
CUDA/HIP: add support for selectable warp size to mmv (llama/11519)	uvos	More...				5 months ago
HIP: add GGML_CUDA_CC_IS_* for amd familys as increasing cc archtectures for amd gpus are not supersets of eatch other (llama/11601)	uvos	More...				5 months ago
CUDA: use mma PTX instructions for FlashAttention (llama/11583)	Johannes Gäßler	More...				5 months ago
`ci`: use sccache on windows instead of ccache (llama/11545)	Olivier Chafik	More...				5 months ago
HIP: require at least HIP 5.5	uvos	More...				5 months ago
HIP: Prepare reduction operators for wave 64	uvos	More...				5 months ago
vulkan: implement initial support for IQ2 and IQ3 quantizations (llama/11360)	Rémy Oudompheng	More...				5 months ago
CUDA/HIP: add warp_size to cuda_device_info	uvos	More...				5 months ago
vulkan: Catch pipeline creation failure and print an error message (llama/11436)	Jeff Bolz	More...				5 months ago
HIP: Supress transformation warning in softmax.cu	uvos	More...				5 months ago
HIP: Only call rocblas_initialize on rocblas versions with the multiple instantation bug (llama/11080)	Nikita Sarychev	More...				5 months ago
cmake : don't fail on `GGML_CPU=OFF` (llama/11457)	someone13574	More...				5 months ago
SYCL : SOFTMAX F16 mask support and other fixes (llama/11261)	Akarshan Biswas	More...				5 months ago
AMD: parse the architecture as supplied by gcnArchName (llama/11244)	Haus1	More...				5 months ago
metal: Handle null returned from MTLCreateSystemDefaultDevice() (llama/11441)	Ihar Hrachyshka	More...				5 months ago
metal : use residency sets (llama/11427)	Georgi Gerganov	More...				5 months ago
cmake: add ggml find package (llama/11369)	bandoti	More...				5 months ago
vulkan: compile shaders on-demand (llama/11406)	Jeff Bolz	More...				5 months ago
Hip: disable VMM on hip as it seams that it dosent work in some configurations (llama/11420)	uvos	More...				5 months ago
hip : Add hipGraph and VMM support to ROCM (llama/11362)	uvos	More...				5 months ago
CUDA: fix FP16 cuBLAS GEMM (llama/11396)	Johannes Gäßler	More...				5 months ago
rocBLAS: Avoid fp32->fp16->fp32 conversion on cdna (llama/11356)	uvos	More...				5 months ago
CPU/CUDA: fix (GQA) mul mat back, add CUDA support (llama/11380)	Johannes Gäßler	More...				5 months ago
cmake : avoid -march=native when reproducible build is wanted (llama/11366)	Bernhard M. Wiedemann	More...				5 months ago
ggml : add option to not print stack on abort (ggml/1081)	William Tambellini	More...				5 months ago
Vulkan-run-test: fix mmq_wg_denoms (llama/11343)	amd-dwang	More...				5 months ago
vulkan: sort shaders for more deterministic binary (llama/11315)	Jeff Bolz	More...				5 months ago
vulkan: fix diag_mask_inf (llama/11323)	Jeff Bolz	More...				5 months ago

←
1
2
…
20
21
22
23
24
25
26
27
28
…
93
94
→