Commit History

metal : single allocation of encode_async block (llama/9747)
6e1b44c

Paul Tsochantaris ggerganov HF Staff commited on

ggml-alloc : remove buffer_id from leaf_alloc (ggml/987)
1a776cc

danbev commited on

scripts : sync amx
f819a74
unverified

ggerganov HF Staff commited on

ggml : alloc ggml_contexts on the heap (#2525)
3ccf40a
unverified

ggerganov HF Staff commited on

ci : fix openblas build (#2511)
b116fe7
unverified

ggerganov HF Staff Tamotsu Takahashi commited on

scripts : add turbo-q8_0 to the benchmark
e923761
unverified

ggerganov HF Staff commited on

whisper : minor compile warning
c06d5f9
unverified

ggerganov HF Staff commited on

whisper : move new-segment callback after DTW step (#2515)
6b8369d
unverified

jettoblack commited on

ruby : fix installation test (#2519)
403eb98
unverified

KitaitiMakoto commited on

ruby : add more APIs (#2518)
8aaba9a
unverified

KitaitiMakoto commited on

ruby : support new-segment callback (#2506)
ae07b89
unverified

KitaitiMakoto commited on

ruby : add Metal support (#2516)
bb2a01d
unverified

KitaitiMakoto commited on

whisper : fix index overflow in token-level timestamp logic (#2505)
de79ec1
unverified

josscii commited on

readme : update links and make commands (#2489)
3767b95
unverified

toboil-features commited on

ruby : fix bindings (#2484)
54b2b95
unverified

KitaitiMakoto commited on

readme : add Vulkan notice (#2488)
005390a
unverified

toboil-features commited on

make : fix GGML_VULKAN=1 build (#2485)
110c8bd
unverified

ggerganov HF Staff commited on

whisper : add dtw preset for large-v3-turbo (#2481)
eae3cdd
unverified

rotemdan commited on

convert : handle max_target_positions (#2477)
c36e329
unverified

CrispStrobe commited on

readme : update the Quick Start section (#2475)
1d23a03
unverified

SalmanFaroz commited on

whisper : add OpenVINO init with state (#2464)
6d5166f
unverified

Sandro Hanea Sandro Hanea commited on

release : v1.7.1
1b81cb9
unverified

ggerganov HF Staff commited on

vulkan : retry allocation with fallback flags (#2451)
9e91cbc
unverified

SRHMorris fdsffdsafds commited on

release : v1.7.0
5abc285
unverified

ggerganov HF Staff commited on

scripts : bench v3-turbo
22b5adf
unverified

ggerganov HF Staff commited on

whisper : remove mel leftover constants (396089f)
505ec31
unverified

ggerganov HF Staff commited on

whisper : zero-out the KV cache upon clear (#2445)
b8af443

ggerganov HF Staff commited on

objc : fix build
564bce1

ggerganov HF Staff commited on

metal : zero-init buffer contexts (#0)
d651546

ggerganov HF Staff commited on

whisper : revert mel-related changes (#0)
7708c26

ggerganov HF Staff commited on

whisper : adapt to latest ggml (skip) (#0)
ad9dd7b

ggerganov HF Staff commited on

ggml : fix typo in example usage ggml_gallocr_new (ggml/984)
30a097b

danbev commited on

ggml : fixes after sync (ggml/983)
237c05a

Diego Devesa commited on

ggml-backend : add device and backend reg interfaces (llama/9707)
9d74d85

Diego Devesa commited on

Fixed dequant precision issues in Q4_1 and Q5_1 (llama/9711)
5239c28

Ouadie EL FAROUKI commited on

ggml-backend : add device and backend reg interfaces (llama/9707)
1bdb50a

Diego Devesa JohannesGaessler commited on

Initial cmake support of SYCL for AMD GPUs (llama/9658)
7d7ac98

Alberto Cabrera Pérez commited on

ggml/ex: calculate accuracy in graph, adapt MNIST (ggml/980)
52069b8

JohannesGaessler commited on

ggml: refactor cross entropy loss CPU impl. (ggml/976)
2a0805f

JohannesGaessler commited on

scripts : sync ggml-backend.cpp
26efed1

ggerganov HF Staff commited on

whisper : fix excessive memory usage (#2443)
afe3785
unverified

ggerganov HF Staff commited on

examples : update dr_wav.h to newer version (#2449)
d678325
unverified

Rahul Vadhyar commited on

talk-llama : sync llama.cpp
c9ddda2

ggerganov HF Staff commited on

metal : reduce command encoding overhead (llama/9698)
43d5a06

ggerganov HF Staff commited on

sync : ggml
c5e24da

ggerganov HF Staff commited on

test: fix OPT_STEP_ADAMW for test-backend-ops (ggml/974)
76aa810

JohannesGaessler commited on

vulkan : mul_mat: fix UB with small warps (ggml/952)
d1a29c6

smeso commited on

ggml : fix ggml_cast (ggml/973)
c44d575

stanimirovb commited on

ggml: fix gradient allocation logic (ggml/966)
ad3f29d

JohannesGaessler commited on