openvino : fix convert-whisper-to-openvino.py (#1890)
dfd53cc
unverified
st-gr
Stefan Grundmann
commited on
Spaces:
Running
Running
Commit History
main : fix file existence check in main.cpp (#1889)
9162df9
unverified
talk-llama : sync llama.cpp
542accf
unverified
make : fix CUBLAS link with WSL (#1878)
b3c9e81
unverified
LBlue
commited on
sync : ggml
cb5b2be
unverified
ggml : resolve merge conflicts (ggml/0)
7ee6ffa
unverified
common : add IQ1_S (ggml/0)
39c054e
unverified
ci : enable -Werror for CUDA builds (llama/5579)
df03a10
unverified
cuda, metal : fix nans in soft_max (llama/5574)
44164ac
unverified
ggml : android and old glibc NUMA incompatibility bugfixes (llama/5557)
0206c2d
unverified
ggml : restore vec dot stride arg names (llama/5453)
de4041f
unverified
ci : fix wikitext url + compile warnings (llama/5569)
49f0106
unverified
metal : fix unused warnings (llama/0)
d12cda5
unverified
ggml, common, examples, tests : fixed type arguments in printf (llama/5528)
2f3a004
unverified
1.5 bit quantization (llama/5453)
9c3aa6a
unverified
ggml : add ALiBi support for ggml_soft_max_ext (llama/5488)
26c019a
unverified
cmake : fix VULKAN and ROCm builds (llama/5525)
ae570e4
unverified
ggml : add numa options (llama/5377)
7c952d2
unverified
cuda : print message when initialization fails (llama/5512)
1f047ca
unverified
slaren
commited on
vulkan: Find optimal memory type but with fallback (llama/5381)
24e2319
unverified
Early return for zero size calls to get_tensor. (llama/5482)
f1f5c00
unverified
ggml-quants : fix compiler warnings (shadow variable) (llama/5472)
e538f25
unverified
ggml-sycl: Replace 3d ops with macro (llama/5458)
12970f1
unverified
Abhilash Majumder
commited on
build : update CBLAS flags + fix unused var warning (#0)
496c0f1
unverified
main : check if input files exist before proceeding (#1872)
d625238
unverified
examples : clean up common code (#1871)
da3cdf4
unverified
models : fix openvino setup info (#1874)
7d4b654
unverified
Jumper775
commited on
models : add update py requirements
a60f965
unverified
swift : package no longer use ggml dependency (#1861)
df6227e
unverified
whisper : fix external encoder (#1860)
3538ca9
unverified
sync : ggml
f0a0087
unverified
ggml-alloc : allocate all leafs as if they were inputs (ggml/731)
a512417
unverified
slaren
commited on
talk-llama : sync llama.cpp
aa42df9
unverified
sync : ggml
be7d266
unverified
ggml-backend : sync remnant
3f5165f
unverified
CUDA: mul_mat_vec_q tiling, refactor mul mat logic (llama/5434)
c0cfa9b
unverified
vulkan: only use M-sized matmul on Apple GPUs (llama/5412)
350284e
unverified
Sergio López
commited on
ggml : fix compile warnings (unused vars) (llama/4966)
97fa2e3
unverified
ggml : add mmla kernels for quantized GEMM (llama/4966)
0d50a29
unverified
snadampal
commited on
metal : use autoreleasepool to avoid memory leaks (llama/5437)
c276f12
unverified
ggml-alloc : v3 (ggml/727)
5cffd6f
unverified
slaren
commited on
examples : added audio_ctx argument to main and server (#1857)
469988b
unverified
metal : option to embed MSL source into compiled binary (#1842)
a46b62a
unverified
Didzis Gosko
commited on
examples : initialize context params properly (#1852)
3443ee7
unverified
talk-llama : sync llama.cpp
e6d6e1d
unverified
sync : ggml
94800c5
unverified
src : relocate new backend sources
44cd2d4
unverified
ggml : fix `error C2078: too many initializers` for MSVC ARM64 (llama/5404)
8ebb36c
unverified
Michael Podvitskiy
commited on