Spaces:
Running
Running
Commit History
whisper : add grammar-based sampling (#1229) 46f0c56 unverified
whisper : add full CUDA and Metal offloading (#1472) da4acca unverified
whisper : add support for large v3 (#1444) 9908abb unverified
sync : ggml (backend v2, k-quants, CUDA opts, Metal opts, etc.) (#1422) 7006035 unverified
metal : add F32 support + update bench output 02d7878 unverified
whisper : Metal and ggml-alloc support (#1270) 714ee6b unverified
build : do not use _GNU_SOURCE gratuitously (#1129) beefa34 unverified
Przemysław Pawełczyk commited on
make : fix detection of AVX2 on macOS (#1250) 272633a unverified
Didzis Gosko commited on
make : improve cpuinfo handling on x86 hosts (#1238) 16b5542 unverified
Przemysław Pawełczyk commited on
make : use cpuinfo in MSYS2 to enable x86 ISA extensions on the host (#1216) 54be145 unverified
Przemysław Pawełczyk commited on
make : add support for building on DragonFlyBSD/NetBSD/OpenBSD (#1212) 02b8e07 unverified
Przemysław Pawełczyk commited on
ggml : detect SSSE3 (#1211) 82a619c unverified
Przemysław Pawełczyk commited on
examples : vim plugin and LSP server (#1144) 358f6c9 unverified
AustinMroz commited on
whisper : initial hipBLAS support (#1209) e093092 unverified
ardfork commited on
build : fix OpenBLAS detection under Arch Linux (#1173) 1551f4e unverified
Marcin Mielniczuk commited on
make : fix Linux machines supporting AVX1 not AVX2 (#1162) e251342 unverified
make : simplify Makefile (#1147) 52b3f80 unverified
alonfaraj commited on
make : fix CLBlast build on MacOS (#1120) 232f2a8 unverified
Christian commited on
make : check nvcc version and set flag (#1115) 01bbf00 unverified
alonfaraj commited on
make : tests can be called as "make tests base.en" (#1113) 1f5c1b8 unverified
Jose commited on
samples : add a larger (30min) sample (#1092) 8453bfd unverified
whisper : support speaker segmentation (local diarization) of mono audio via tinydiarize (#1058) eedbf0c unverified
Revert "ggml : do not use _GNU_SOURCE gratuitously (#1027)" 1e5ddb0 unverified
talk-llama : fix build on macOS (#1062) 15d6fd8 unverified
Przemysław Pawełczyk commited on
ggml : do not use _GNU_SOURCE gratuitously (#1027) 3a69cdf unverified
Przemysław Pawełczyk commited on
opencl : sync latest ggml-opencl ced3ca3 unverified
make : update cuBLAS build both x86 and aarch64 (#1015) 5d4a28f unverified
byte-6174 commited on
make : fix for CUDA native not working as an option on Ubuntu (#1012) 1807a31 unverified
KP Kaiser commited on
build : CLBlast support as in llama.cpp (#862) 6a785f1 unverified
Vulcan commited on
ggml : fix 32-bit ARM build + quantization 87ee234
whisper : add integer quantization support (#540) a5f8f3c unverified
whisper : add GPU support via cuBLAS (#834) d91d7d9 unverified
build : add WHISPER_COREML_ALLOW_FALLBACK to make / CMake (#812) 49fb1c6 unverified
whisper : add Core ML support (#566) 1fd4bde unverified
make : disable avx in case f16c is not available (#706) 05bed31 unverified
duthils commited on
ggml : sync latest changes from ggml and llama.cpp 3bd52ce unverified
make : 32-bit ARM flags (#486) 4fc344e unverified
talk-llama : add new example + sync ggml from llama.cpp (#664) a8c74e6 unverified
make : fix MUSL Linux build (#576) 51936e8 unverified
make : add -DNDEBUG compile flag 27ce621 unverified
make : add "-mcpu=native" when building for aarch64 (#532) 3f06aea unverified
FlippFuzz commited on
examples : refactor in order to reuse code and reduce duplication (#482) acbd6f7 unverified
whisper : PPC64 big-endian support (#398) 239569b unverified
fitzsim commited on
