ci: fix SYCL build (#2943)
95a0dbf
unverified
Akarshan Biswas
commited on
Spaces:
Running
Running
Commit History
examples : reduce initial memory to 512MB (#2939)
a406dda
unverified
examples : fix nthread parsing in whisper.wasm (#2938)
603da69
unverified
examples : fix request path for local worker files (#2937)
0d0eed6
unverified
ggml : add logging for native build options/vars (#2935)
aaf8a91
unverified
whisper : enhance model download scripts functionality and resolve compiler warning (#2925)
69f99f1
unverified
Peter
commited on
whisper : initialize decoder's rng with unique seed (#2932)
6322856
unverified
ci : remove CMAKE_CUDA_ARCHITECTURES in windows-cublas (#2923)
6f57276
unverified
whisper : update default model download directory behavior to use current working directory when script is in /bin/ directory (#2924)
78726ec
unverified
Peter
commited on
whisper.swiftui : Add Core ML support to README [no ci] (#2921)
be8fe47
unverified
readme : update Python version to 3.11 for Core ML support [no -ci] (#2919)
284138f
unverified
whisper : add check for CPU backend initialization (#2918)
ae8d838
unverified
examples : update whisper.objc README.md (#2916)
0389e41
unverified
ci : increase windows-cublas evict-old-files to 5d (#2915)
8b6c315
unverified
xcframework : add support for CoreML to ios/macOS (#2912)
8441d70
unverified
examples : add WHISPER_SDL2 check to deprecation executables (#2911)
d1d1943
unverified
ci : use ninja and fix caching for windows-cublas (#2910)
d5085df
unverified
examples : update wasm examples to include server.py [no ci] (#2908)
937218a
unverified
examples : command.wasm updates (#2904)
0db3249
unverified
ci : refactor cuda toolkit installation steps (#2902)
0a6a7c1
unverified
go : add Encoder Begin Callback (#2900)
6eea7b7
unverified
Amanda Der Bedrosian
Amanda Der Bedrosian
commited on
ci : add ccache action to windows-cublas job (#2893)
ab959d1
unverified
whisper : fix compiler warnings in whisper.cpp (#2895)
bfa2ae7
unverified
ci : add missing env.branch_name to build.yml (#2896)
d237704
unverified
whisper : enable compiler warnings for src (#2891)
a216359
unverified
ci : add release job and include xcframework (#2889)
1f9c279
unverified
examples : use xcframework in whisper.objc example (#2882)
d520f58
unverified
whisper : add option to use system-installed GGML (#2887)
ce83587
unverified
Peter
commited on
convert : update convert-h5-to-ggml.py (#2840)
3d457ce
unverified
Anders Bjarby
commited on
examples : add GGML_USE_CPU=ON flag to whisper.objc (#2880)
749d15b
unverified
ggml-ci: update input env variables to GG_BUILD_ (#2879)
e5e2e61
unverified
ggml-ci: add run.sh (#2877)
3e264ce
unverified
examples : add dl to the list of libraries linked (#2875)
dc2a512
unverified
whisper: add xcframework build script (#2873)
9797241
unverified
objc : fix build, tmp remove GPU support, use C++17
e1b5e01
cmake : fix ggml-config (ggml/0)
40f0325
sync : ggml
f18e587
ggml-cpu: faster AVX2 variant for IQ1_M (llama/12216)
591cbfb
Rémy O
commited on
metal : simplify kernel arguments using a struct (ggml/3229) (llama/12194)
092277a
BB-fat
alexju
commited on
metal : fix default.metallib build (llama/12224)
838efb6
opencl: Noncontiguous `norm`, `rms_norm`, disable `fp16` for some ops (llama/12217)
94449e3
lhez
commited on
cmake : fix undefined reference errors for std::filesystem in ggml (#12092) (llama/12094)
dc68418
xiaofei
Ray Lee
commited on
CUDA: fix FA logic for PTX 7.0 and CC >= 7.5 (llama/12222)
4dc8a81
HIP/CUDA: set the paramerter value in maintain_cuda_graph instead of replaceing it. (llama/12209)
18afa4b
uvos
commited on
opencl : fix buffer alignment (llama/12197)
7d25156
opencl : fix `ulong` kernel args were set from `int` variables (llama/12174)
67ffff0
opencl : fix profile-related errors (llama/12095)
e11a847
simon886212
ubuntu
commited on
ggml-cpu: Faster IQ1 mul_mat_vec on AVX2 using BMI2 instructions (llama/12154)
05466a9
Rémy O
commited on
SYCL: Disable f16 Unary OPs as not supported by the kernels (llama/12201)
723b8b4
Akarshan Biswas
commited on
