ci : fix variable names in GitHub actions config (#1440)
66cb760
unverified
iamthad
commited on
Spaces:
Running
Running
Commit History
talk-llama : fix n_gpu_layers usage again (#1442)
37d6862
unverified
whisper : add missing about callback initializers
a94a8ce
unverified
examples : fix n_gpu_layers usage in talk-llama (#1441)
e0ea7d1
unverified
whisper : add support for new distilled Whisper models (#1424)
a570c92
unverified
cuda : fix HIPBLAS build
46033e6
unverified
sync : ggml (backend v2, k-quants, CUDA opts, Metal opts, etc.) (#1422)
7006035
unverified
models : use absolute paths for the converted model (#1356)
6023f2d
unverified
bobqianic
commited on
talk-llama : move up-to-date demo to top (#1417)
060e781
unverified
talk-llama : add an up-to-date demo video
b41f03a
unverified
examples : Implement JSON output for Token-Level data in main (#1358)
d166741
unverified
models : Faster download for models on windows using BitTransfer (#1404)
b1a3c5a
unverified
WhiteOlivierus
commited on
README : Update README in stream to clarify where to compile from (Issue #1400)
51306fa
unverified
ai-at-home
AI @ Home
bobqianic
commited on
binding : Expose the audio_ctx param through the Go binding (#1368)
8e7b807
unverified
README : fix typo (#1362)
d676563
unverified
jorismertz
commited on
docker : Add dockerfile for cublas (#1286)
75470cc
unverified
joecryptotoo
bobqianic
commited on
whisper : abort callback improvements (#1345)
776adfd
unverified
mkiol
commited on
cmake : Abort the build if a requested feature could not be configured (#1350)
fb91f57
unverified
Marcin Mielniczuk
commited on
cmake : Prefer pkg-config while looking for BLAS (#1349)
67693c8
unverified
Marcin Mielniczuk
commited on
models : add conversion scripts from HuggingFace models to CoreML (#1304)
756cd4b
unverified
whisper : add abort callback (#1335)
08ba486
unverified
mkiol
commited on
examples : move wav_writer from stream.cpp to common.h (#1317)
6c20dfb
unverified
bobqianic
commited on
whisper : add missing speaker turn API function for whisper_state (#1330)
00ca046
unverified
Didzis Gosko
commited on
examples: Update the README for Talk - fixing the gpt2 URL (#1334)
751235c
unverified
extra: Add benchmark script implemented in Python (#1298)
c587102
unverified
Neil Chudleigh
commited on
Examples: Add save audio to file option in stream.cpp (#1310)
30cdb60
unverified
litong
bobqianic
commited on
readme: Fix spelling error (#1290)
fa72f91
unverified
JJ
commited on
examples: Update README.md of main.cpp (#1306)
a2537c1
unverified
binding : fix ruby build by adding missing ggml-alloc (#1305)
b062b12
unverified
bench: fix missing include <cstring> (#1303)
eb68655
unverified
Evgeny Kuznetsov
commited on
whisper : increase tokenizer buffer (close #1259)
c4e797f
unverified
talk-llama : update to latest llama.cpp
1493d0c
unverified
sync : ggml (const correctness)
4ce2d25
unverified
metal : restore matrix x vector f16_f32 kerenls for now
2dd8c56
unverified
metal : add F32 support + update bench output
02d7878
unverified
whisper : Metal and ggml-alloc support (#1270)
714ee6b
unverified
whisper : fix bench regression + fix performance when using CPU BLAS (#1275)
abbf5f2
unverified
whisper : faster beam_search sampling via reduced KV cache copies (#1243)
93140af
unverified
java : fixed signing of java artifact using gradle (#1267)
d51aaa6
unverified
ci : try to fix gradle action (#1265)
e580f4e
unverified
gitignore : update
d55a6cc
unverified
sync : ggml (HBM + Metal + style) (#1264)
88deeba
unverified
ci : upgrade gradle to 2.4.2 (#1263)
a88e806
unverified
sync : ggml (CUDA faster rope)
44e3164
unverified
cmake : noramlize case (#1129)
c34de91
unverified
build : do not use _GNU_SOURCE gratuitously (#1129)
beefa34
unverified
Przemysław Pawełczyk
commited on
examples : fix build + compile warnings (close #1256)
2cfc05a
unverified
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