Hugging Face's logo

Spaces:
natasa365
/
whisper.cpp
Sleeping

App Files Community
whisper.cpp

Commit History

Disable iqx on windows as WA (llama/6435)
7a97623
unverified

hengyu commited on

Vulkan k-quant mmq and ggml-backend offload functionality (llama/6155)
1ff7b08
unverified

OccamRazor commited on

fix set main gpu crash (llama/6339)
3bdb5e6
unverified

Neo Zhang Jianyu commited on

ggml : fix bounds checking of zero size views (llama/6347)
80db462
unverified

slaren commited on

backend : fix typo in scheduler documentation (ggml/781)
e7ddd12
unverified

danbev commited on

extra : sync ggml-cuda folder
fa0af15
unverified

ggerganov commited on

ggml: bypass code incompatible with CUDA < 11.1 (#2020)
32f4e35
unverified

primenko commited on

ci : add building in MSYS2 environments (Windows) (#1994)
08d5ab5
unverified

Przemysław Pawełczyk commited on

build : use pkg-config for OpenBLAS (#1778)
d5d466c
unverified

Przemysław Pawełczyk commited on

main : add command-style grammar (#1998)
7e6ea10
unverified

ulatekh ggerganov commited on

make : add grammar parser to common objects
b1f3938
unverified

ggerganov commited on

sync : ggml (#2001)
cbbfa9e
unverified

ggerganov commited on

whisper : improve handling of prompts (#1981)
15949a9
unverified

ggerganov commited on

whisper : improve support for distil-large-v3 (#1982)
749004e
unverified

Sanchit Gandhi commited on

ruby : fix build (#1980)
20374d7
unverified

ggerganov commited on

docker : libcuda.so.1 in PATH (#1966)
2cd0d06
unverified

Tiago Fassoni commited on

readme : add Fedora dependencies (#1970)
afc6b1a
unverified

Mohammadreza Hendiani commited on

whisper : token-level timestamps with DTW (#1485)
ce7ca09
unverified

denersc ggerganov commited on

examples : rename --audio-context to --audio-ctx per help text (#1953)
8e9c985
unverified

joliss commited on

whisper : set outputs from conv graph (#1959)
62505d4
unverified

ggerganov commited on

alloc : fix allocation data of pre-allocated leafs
0c378f2
unverified

slaren commited on

cmake : copy ggml-common.h to bin
f592e46
unverified

ggerganov commited on

gitignore : .vimspector.json
b593d9a
unverified

ggerganov commited on

talk-llama : sync llama.cpp
14e824b
unverified

ggerganov commited on

sync : ggml
1701a5d
unverified

ggerganov commited on

update examples and tests
007ebd7
unverified

slaren commited on

ggml : add ggml-common.h
8cdfa17
unverified

ggerganov commited on

ggml : designate enum vals for integer types (llama/6050)
0bd0c7a
unverified

ggerganov commited on

metal : build metallib + fix embed path (llama/6015)
27311ef
unverified

ggerganov commited on

llama : add pipeline parallelism support (llama/6017)
b5bb3f3
unverified

slaren compilade ggerganov commited on

Update get version (llama/6025)
9a4e508
unverified

AidanBeltonS commited on

ggml : reuse quantum structs across backends (llama/5943)
bb0625f
unverified

ggerganov commited on

ggml : fix UB in IQ2_S and IQ3_S (llama/6012)
0c552df
unverified

ggerganov commited on

sycl : update IQ1_S kernels (WIP - not working!) (llama/5995)
16dc72c
unverified

ggerganov commited on

1.5 bit: we can do even better (llama/5999)
36cc71e
unverified

Kawrakow ikawrakow commited on

ggml, ci : Windows ARM runner and build fixes (llama/5979)
507b9dd
unverified

Michael Podvitskiy commited on

Better 1.5 bit quantization (llama/5971)
f3a62cc
unverified

Kawrakow ikawrakow commited on

Add q3_s and q1_s (llama/5886)
2957823
unverified

Abhilash Majumder commited on

metal : move mm_id indices to shared mem (llama/5982)
1350705
unverified

ggerganov commited on

ggml : fix unnecessary f32 -> f16 -> f32 casts (mmla) (llama/5951)
cb8bbaa
unverified

ggerganov commited on

ggml : remove old quantization functions (llama/5942)
11a2545
unverified

ggerganov commited on

ggml : add ggml-common.h to deduplicate shared code (llama/5940)
0a37735
unverified

ggerganov commited on

llama : support Mamba Selective State Space Models (llama/5328)
224fbc2
unverified

compilade commited on

extra : update sync scripts after ggml-common.h
2e29431
unverified

ggerganov commited on

whisper : document whisper_batch.n_seq_id (#1942)
f08549e
unverified

josharian commited on

whisper : improve beam search candidate diversity (#1947)
6e9276c
unverified

josharian commited on

bindings/go : add linker flags to make metal work (#1944)
3dee0de
unverified

josharian commited on

whisper : make beam candidate sort more stable (#1943)
1316242
unverified

josharian commited on

ggml : try fix 32-bit arm compat (#1938)
6ea3354
unverified

ggerganov commited on

talk-llama : use llama_decode instead of llama_eval
301b000
unverified

ggerganov commited on