Spaces:
Running
Running
Commit History
ci : add mirror for ports.ubuntu.com (ARM packages) (#3221)
17ba7f5
unverified
bindings.java : apply whisperParams in fullTranscribeWithTime instead of ignoring them (#3201)
18fb7d6
unverified
Joas Dev
commited on
musa: correct MUSA SDK rc4.0.1 download URL (#3217)
90efe84
unverified
R0CKSTAR
commited on
ci : use mirrors.kernel.org for Ubuntu packages (#3220)
62dd144
unverified
node : add language detection support (#3190)
9994342
unverified
talk-llama : sync llama.cpp
58220b6
sync : ggml
337f4d9
threading: support for GGML_SCHED_PRIO_LOW, update thread info on Windows to avoid throttling (llama/12995)
d5d55f2
Max Krasnyansky
Diego Devesa
commited on
CUDA: add a prop in ggml_cuda_device_infor for distinguish iGPU or dGPU in cuda (#13856) (llama/13895)
a75e157
CUDA: fix typo in FlashAttention code (llama/13926)
6fb9674
sched : avoid changing cur_copy when a graph is already allocated (llama/13922)
1c0a5c0
Diego Devesa
commited on
cuda : prevent using split buffers with 3d/4d matrices (llama/13919)
6b6155b
Diego Devesa
commited on
SYCL: Add mrope kernel (llama/13755)
e4b1812
Akarshan Biswas
commited on
cmake: Guard GGML_CPU_ALL_VARIANTS by architecture (llama/13890)
a434936
Christian Kastner
commited on
arm64: optimize q4_k_q8_k kernel with i8mm (llama/13886)
026ea5b
Yibo Cai
commited on
cmake: Factor out CPU architecture detection (llama/13883)
b436dcc
Christian Kastner
commited on
ggml: aarch64: Implement SVE F32 kernels for Mamba Sequential Scan Algorithm (llama/13882)
bfc960a
ggml: aarch64: Implement SVE F32 kernels for vector functions (llama/13843)
7941e9b
Vineel Abhinav
commited on
CUDA: fix FA tg at long context for CC >= 8.9 (llama/13852)
d9bd7ce
CANN: Add SOC TYPE printing in cmake configuration (llama/13837)
abeb563
leo-pony
commited on
opencl: add new ops - `argsort`, `div`, `sub`, `addrows`, `sigmoid`, `group_norm` (llama/13787)
1ab0f23
lhez
commited on
opencl: mark `mul_mat` `f32f32` as supporting non-contiguous tensors (llama/13790)
4473109
lhez
commited on
vulkan: use timestamp queries for GGML_VULKAN_PERF (llama/13817)
56ddc5b
SYCL: add gelu_erf kernel (llama/13749)
49a9b40
Akarshan Biswas
Atharva Dubey
commited on
ggml : add ggml_repeat_4d (llama/13824)
3fe8af8
vulkan : Remove unexpected ; (ggml/1253)
c4be6fb
Kai Pastor
commited on
cmake : Fix broken CMake error messages (ggml/1252)
67baecc
Kai Pastor
commited on
ggml : remove ggml_graph_import and ggml_graph_export declarations (ggml/1247)
3c9a1d2
ruby : add Core ML support (#3214)
72cecc9
unverified
vad : revisit timestamp alignment/mapping (#3173)
f198f02
unverified
ruby : handle build options on installation (#3206)
7953154
unverified
ggml : Fix backtrace breaking Windows build (#3203)
3f352bd
unverified
Daniel Tang
commited on
sync : ggml
eb81a6a
ggml : install dynamic backends (ggml/1240)
1909e63
ggml : Print backtrace on uncaught C++ exceptions (ggml/1232)
1459465
Daniel Tang
commited on
whisper : remove whisper_load_backends function (#3196)
0cae2d6
unverified
ruby : add VAD support, migration to Ruby's newer API (#3197)
1ee7297
unverified
whisper : install shared libs when using GGML_BACKEND_DL (#3195)
f44915b
unverified
tests : add a new benchmark test for long-form audio (#3185)
2d5018c
unverified
ci : update windows-blas uploads action (#3192)
3b0cb7a
unverified
sync : fix builds - musa, ruby
84007bb
talk-llama : sync llama.cpp
5d037b9
sync : ggml
78bfd81
ggml : riscv: add xtheadvector support (llama/13720)
4790d5d
xctan
commited on
ggml-cpu: x86 feature detection is specific to x86 (llama/13811)
d86ba47
Christian Kastner
commited on
ggml : allow CUDA graphs when using pipeline parallelism (llama/13814)
b85e3c0
Diego Devesa
commited on
cuda : avoid cuGetErrorString (llama/13791)
cdf95d3
SYCL: Add non contiguous support in RMS_NORM and NORM kernels (llama/13611)
5de15cd
Akarshan Biswas
commited on
sycl: Add more debug prints (llama/13640)
4da3fb6
Romain Biessy
commited on