Commit History

talk-llama : update to latest llama.cpp
1493d0c
unverified

ggerganov commited on

sync : ggml (const correctness)
4ce2d25
unverified

ggerganov commited on

metal : restore matrix x vector f16_f32 kerenls for now
2dd8c56
unverified

ggerganov commited on

metal : add F32 support + update bench output
02d7878
unverified

ggerganov commited on

whisper : Metal and ggml-alloc support (#1270)
714ee6b
unverified

ggerganov commited on

whisper : fix bench regression + fix performance when using CPU BLAS (#1275)
abbf5f2
unverified

ggerganov commited on

whisper : faster beam_search sampling via reduced KV cache copies (#1243)
93140af
unverified

bobqianic ggerganov commited on

java : fixed signing of java artifact using gradle (#1267)
d51aaa6
unverified

nalbion commited on

ci : try to fix gradle action (#1265)
e580f4e
unverified

ggerganov commited on

gitignore : update
d55a6cc
unverified

ggerganov commited on

sync : ggml (HBM + Metal + style) (#1264)
88deeba
unverified

ggerganov commited on

ci : upgrade gradle to 2.4.2 (#1263)
a88e806
unverified

ggerganov commited on

sync : ggml (CUDA faster rope)
44e3164
unverified

ggerganov commited on

cmake : noramlize case (#1129)
c34de91
unverified

ggerganov commited on

build : do not use _GNU_SOURCE gratuitously (#1129)
beefa34
unverified

Przemysław Pawełczyk commited on

examples : fix build + compile warnings (close #1256)
2cfc05a
unverified

ggerganov commited on

models : add quantum models to download-ggml-model.sh (#1235)
b2abb1b
unverified

Neil Chudleigh commited on

whisper.android : bump gradle plugin and dependencies + a lint pass (#1255)
887812b
unverified

Digipom commited on

sign jar for Maven Central repo
0422ae0

nalbion commited on

whisper.android : address ARM's big.LITTLE arch by checking cpu info (#1254)
a3cb126
unverified

Digipom commited on

make : fix detection of AVX2 on macOS (#1250)
272633a
unverified

Didzis Gosko commited on

ggml : posixify pagesize (#1251)
4902c26
unverified

Przemysław Pawełczyk commited on

configured publishing.repositories
6d037ea

nalbion commited on

ggml : sync latest llama.cpp (view_src + alloc improvements) (#1247)
8bb66c1
unverified

ggerganov commited on

make : improve cpuinfo handling on x86 hosts (#1238)
16b5542
unverified

Przemysław Pawełczyk commited on

ggml : sync (ggml-alloc, GPU, eps, etc.) (#1220)
d41ba35
unverified

ggerganov commited on

OSSRH_USERNAME -> JIRA_USER
b490422
unverified

nalbion commited on

build-root-directory: bindings/java
ddc216e
unverified

nalbion commited on

ci : enable java package publishing (#1228)
75d5513
unverified

ggerganov commited on

ggml : fix compilation errors incurred by -Werror (#1227)
45ef7b5
unverified

ChangSeok Oh commited on

whisper.android : fix cmake multiple libraries build (#1224)
96ada58
unverified

jhenhong commited on

coreml : wrap inference call in @autoreleasepool to fix memory leak (#1218)
7670fc1
unverified

Dener Stassun 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 : fix compiling when SSE3 is available but not SSSE3 (#1210)
b7995b7
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

whisper : allow whisper_full from mel spectrogram - no audio (#1214)
8ae21a0
unverified

ggerganov jbrough commited on

whisper : significantly improve the inference quality (#1148)
7b59286
unverified

bobqianic ggerganov commited on

whisper.android : migrate from ndk-build to CMake (#1204)
df7ed53
unverified

junkfood commited on

main : log probs to text file (#1205)
26a54a0
unverified

jbyu ggerganov commited on

whisper : minor fixes (#1154)
fc4185e
unverified

csukuangfj 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

Eric Swanson ggerganov commited on

whisper : add precalculated values of sin/cos for speeding up FFT (#1142)
721a4d5
unverified

Alexandr Graschenkov ggerganov bobqianic commited on

make : simplify Makefile (#1147)
52b3f80
unverified

alonfaraj commited on

cmake : fix PowerPC build failures introduced in #1174 (#1196)
35adb54
unverified

Marcin Mielniczuk commited on

Fix AVX etc. under GCC/CMake (#1174)
87c002e
unverified

Marcin Mielniczuk commited on