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 05, 2024 — Jun 05, 2025 Showing page 29 of 91 Search / Filter on:
whisper : use backend registry (#0)	Georgi Gerganov	More...				7 months ago
ggml/sched : do not skip views in pre-assignments	slaren	More...				7 months ago
vulkan: copy iq4_nl LUT into shared memory (llama/10409)	Jeff Bolz	More...				7 months ago
vulkan: further optimize mul_mat_vec using larger loads (llama/10387)	Jeff Bolz	More...				7 months ago
add cmake rvv support (llama/10411)	haopeng	More...				7 months ago
whisper : adapt to new ggml (wip)	Georgi Gerganov	More...				7 months ago
talk-llama : sync llama.cpp	Georgi Gerganov	More...				7 months ago
sync : ggml	Georgi Gerganov	More...				7 months ago
ggml : sync resolve (skip) (#0)	Georgi Gerganov	More...				7 months ago
scripts : update sync	Georgi Gerganov	More...				7 months ago
release : v1.7.2	Georgi Gerganov	More...				7 months ago
Add required ggml-base and backend libs to cmake pkg (llama/10407)	bandoti	More...				7 months ago
cuda : fix CUDA_FLAGS not being applied (llama/10403)	Diego Devesa	More...				7 months ago
sycl : Add option to set the SYCL architecture for all targets (llama/10266)	Romain Biessy	More...				7 months ago
vulkan: Optimize soft_max (llama/10301)	Jeff Bolz	More...				7 months ago
sycl: Revert MUL_MAT_OP support changes (llama/10385)	Alberto Cabrera Pérez	More...				7 months ago
cuda : only use native when supported by cmake (llama/10389)	Diego Devesa	More...				7 months ago
vulkan: remove use of null initializer (llama/10372)	Jeff Bolz	More...				7 months ago
metal : fox offset integer overflows in im2col (ggml/1015)	Plamen Minev	More...				7 months ago
sycl: fix example build (#2570)	Stefan Sydow	More...				7 months ago
Vulkan: Fix device info output format specifiers (llama/10366)	0cc4m	More...				7 months ago
metal : add `GGML_UNARY_OP_ELU` kernel (ggml/1018)	PAB	More...				7 months ago
CUDA: fix MMV kernel being used for FP16 src1 (llama/10357)	Johannes Gäßler	More...				7 months ago
CMake: fix typo in comment [no ci] (llama/10360)	Johannes Gäßler	More...				7 months ago
llama : only use default buffer types for the KV cache (llama/10358)	Diego Devesa	More...				7 months ago
metal : refactor kernel args into structs (llama/10238)	Georgi Gerganov	More...				7 months ago
ggml : fix undefined reference to 'getcpu' (llama/10354)	FirstTimeEZ	More...				7 months ago
CUDA: remove DMMV, consolidate F16 mult mat vec (llama/10318)	Johannes Gäßler	More...				7 months ago
CMake: default to -arch=native for CUDA build (llama/10320)	Johannes Gäßler	More...				7 months ago
ggml : fix possible buffer use after free in sched reserve (llama/9930)	Diego Devesa	More...				7 months ago

←
1
2
…
25
26
27
28
29
30
31
32
33
…
90
91
→