ngxson/llama.cpp

Pull Requests Commits
fix tests
ngxson committed 1 year ago
3bea2e6a
fix typo
ngxson committed 1 year ago
468551e7
update server docs
ngxson committed 1 year ago
7fee2037
fix tests
ngxson committed 1 year ago
a533aac1
protect /props endpoint
ngxson committed 1 year ago
7560ecb3
server : more explicit endpoint access settings
ngxson committed 1 year ago
460ec6f4
metal : single allocation of encode_async block (#9747)
ptsochantaris committed 1 year ago
Verified 96b69121
contrib : simplify + minor edits [no ci]
ggerganov committed 1 year ago
Verified d5cb8684
readme : fix typo [no ci]
ggerganov committed 1 year ago
Verified f4b2dcdf
sync : llama.cpp
ggerganov committed 1 year ago
Verified b6d6c528
vulkan : retry allocation with fallback flags (whisper/2451)
SRHMorris committed 1 year ago
Verified b0915d5b
rerank : use [SEP] token instead of [BOS] (#9737)
ggerganov committed 1 year ago
Verified 8c475b97
sync : ggml
ggerganov committed 1 year ago
Verified 58b16695
metal : zero-init buffer contexts (whisper/0)
ggerganov committed 1 year ago
Verified 905f5485
Add Llama Assistant (#9744)
vietanhdev committed 1 year ago
Verified 71967c2a
sync : ggml
ggerganov committed 1 year ago
Verified 17880771
ggml : fix typo in example usage ggml_gallocr_new (ggml/984)
danbev committed 1 year ago
Verified 55951c01
ggml : fixes after sync (ggml/983)
slaren committed 1 year ago
Verified ff565769
ci : fine-grant permission (#9710)
ngxson committed 1 year ago
Verified f3fdcfaa
Fixed RNG seed docs (#9723)
d-kleine committed 1 year ago
Verified 133c7b46
metal : remove abort (skip) (ggml/0)
ggerganov committed 1 year ago
Verified d5ed2b92
sync : ggml
ggerganov committed 1 year ago
Verified 1bb8a64e
ggml/ex: calculate accuracy in graph, adapt MNIST (ggml/980)
JohannesGaessler committed 1 year ago
Verified fabdc3bd
ggml: refactor cross entropy loss CPU impl. (ggml/976)
JohannesGaessler committed 1 year ago
Verified eee39bdc
metal : fix compute pass descriptor autorelease crash (#9718)
jmousseau committed 1 year ago
Verified 5d5ab1e5
ggml-backend : add device description to CPU backend (#9720)
slaren committed 1 year ago
Verified a7ad5535
ggml: unify backend logging mechanism (#9709)
bandoti committed 1 year ago
Verified d6fe7abf
convert : handle tokenizer merges format from transformers 4.45 (#9696)
compilade committed 1 year ago
Verified e3c355ba
rpc : enable vulkan (#9714)
rgerganov committed 1 year ago
Verified 841713e1
Fixed dequant precision issues in Q4_1 and Q5_1 (#9711)
OuadiElfarouki committed 1 year ago
Verified 56399714
Terms Of Use Privacy Policy Refund Policy Impressum