Spaces:
Sleeping
Sleeping
Commit History
ruby : change homepage URI in Ruby gemspec (#3007)
a1b00a9
unverified
tests : add script to benchmark whisper.cpp on LibriSpeech corpus (#2999)
ba518eb
unverified
whisper : fix "bench-all outputs an invalid result on larger models" (#3002)
b6c9266
unverified
rename : ggerganov -> ggml-org (#3005)
f816f88
unverified
examples : update server.py to match github pages app [no ci] (#3004)
0fdd602
unverified
whisper.wasm : fix unknown language issue (#3000)
d53c30c
unverified
examples : add new sources
2a8a6b4
sync : ggml
612ed3c
cpu: move all the operators into a separate c++ file (except mul_mat) (ggml/1167)
0754d43
cmdr2
Diego Devesa
commited on
docs : add xcframework section to README.md [no ci] (#2997)
6688a2b
unverified
readme : update roadmap link
10978e6
unverified
release : v1.7.5
cd6dfb3
bench : update numbers [no ci] (#2993)
afce5f4
unverified
sync : ggml
524319a
get_rows and dup optimization (llama/12671)
ffa5f14
opencl : fix memory allocation size (llama/12649)
b00a8a9
metal : use F32 prec in FA kernels (llama/12688)
a49f5c2
Fix clang warning in gguf_check_reserved_keys (llama/12686)
a00d66c
R0CKSTAR
commited on
vulkan: fix build when glslc doesn't support coopmat (llama/12683)
f91eb88
Wagner Bruna
commited on
SYCL: Rename oneMKL to oneMath (llama/12192)
d89f6fa
Romain Biessy
commited on
SYCL: switch to SYCL namespace (llama/12674)
fe06fa2
Akarshan Biswas
commited on
ggml : faster ssm scan (llama/10558)
a18cd16
a3sh
commited on
Vulkan: Add DP4A MMQ and Q8_1 quantization shader (llama/12135)
06ec111
cmake : fix whitespace (llama/0)
a596e84
tests : remove gh label test-whisper-cli-tiny-en (#2988)
80a0445
unverified
examples : clarify Core ML encoder model usage [no ci] (#2987)
b332af9
unverified
ci : remove intermediate build on push to master (#2986)
1526565
unverified
whisper.objc : fix typo in README.md [no ci] (#2985)
e6ba999
unverified
coreml: fix Whisper to CoreML conversion by disabling SDPA [no ci] (#2979)
bf862e4
unverified
ci : add coreml job that converts base.en to coreml [no ci] (#2981)
26aba7a
unverified
tests : re-enable tests [no ci] (#2977)
8c851e2
unverified
android.java : re-add ggml source updates (#2975)
5dca9f3
unverified
ci : re-enable freeBDS-latest job (#2973)
32bf9c9
unverified
ci : re-enable android_java job (#2958)
e7fbecf
unverified
android : add new ggml source files
69804b5
ruby : add new ggml sources
c5a918e
sync : ggml
db835f2
SYCL: Remove misleading ggml_sycl_op_flatten function (llama/12387)
0a9c73a
Akarshan Biswas
commited on
metal : use constexpr in FA kernels + fix typedef (llama/12659)
c699617
musa: fix all warnings, re-enable `-DLLAMA_FATAL_WARNINGS=ON` in ci and update doc (llama/12611)
12bb60d
R0CKSTAR
commited on
cmake : fix ccache conflict (llama/12522)
22dfdf6
Jay
commited on
cpu : rm unused variable (ggml/1166)
86eb3af
cpu: de-duplicate some of the operators and refactor (ggml/1144)
09f2f18
cmdr2
commited on
cmake: improve Vulkan cooperative matrix support checks (#2966)
4be7f68
unverified
Sandro Hanea
Sandro Hanea
commited on
