 Georgi Gerganov
|
044ec4b2a5
embedding : add EOS token if not present (#899)
|
пре 1 година |
|
Georgi Gerganov
|
77178eedc8
gguf-py : fix dtype check (#6045)
|
пре 1 година |
 Jian Liao
|
15a333260a
readme : improve readme for Llava-1.6 example (#6044)
|
пре 1 година |
 Pierrick Hymbert
|
43241adf22
server: disable debug release type sanitizer, simplify trigger (#6047)
|
пре 1 година |
|
Georgi Gerganov
|
a44bc969e4
llama : fix typo
|
пре 1 година |
 Michael Podvitskiy
|
2c4fb69246
llama : optimize defrag moves + fix fragmentation calculation (#6037)
|
пре 1 година |
 Ondřej Čertík
|
3ca23481dd
gguf-py : add support for I8, I16 and I32 (#6045)
|
пре 1 година |
|
Georgi Gerganov
|
3fe8d7a17f
ggml : designate enum vals for integer types (#6050)
|
пре 1 година |
|
Georgi Gerganov
|
68265ebfc6
embedding : print all resulting embeddings (#899)
|
пре 1 година |
|
Georgi Gerganov
|
381da2d9f0
metal : build metallib + fix embed path (#6015)
|
пре 1 година |
|
Georgi Gerganov
|
0fd6c1f015
embedding : print cosine similarity (#899)
|
пре 1 година |
 Linwei Wang
|
19885d205e
readme : update details about running llama in Termux on Android (#6039)
|
пре 1 година |
|
Georgi Gerganov
|
76a936c893
readme : update API changes and hot topics
|
пре 1 година |
 Clint Herron
|
463628372d
grammar : handle missing "root" node (#6004)
|
пре 1 година |
 slaren
|
f30ea47a87
llama : add pipeline parallelism support (#6017)
|
пре 1 година |
|
slaren
|
d8fd0ccf6a
test-backend-ops : skip CPU backend by default (#6028)
|
пре 1 година |
 AidanBeltonS
|
b3d978600f
Update get version (#6025)
|
пре 1 година |
 Xuan Son Nguyen
|
99b71c068f
Server: Use multi-task for embeddings endpoint (#6001)
|
пре 1 година |
|
slaren
|
306d34be7a
ci : remove tidy-review (#6021)
|
пре 1 година |
|
Georgi Gerganov
|
8030da7afe
ggml : reuse quantum structs across backends (#5943)
|
пре 1 година |
|
Georgi Gerganov
|
184215e783
ggml : fix UB in IQ2_S and IQ3_S (#6012)
|
пре 1 година |
|
Georgi Gerganov
|
48358b2e5b
sycl : update IQ1_S kernels (WIP - not working!) (#5995)
|
пре 1 година |
 gliptic
|
5cdb371731
grammar : fix unnecessarily retained pointer to rules (#6003)
|
пре 1 година |
 Kawrakow
|
44ca159faf
1.5 bit: we can do even better (#5999)
|
пре 1 година |
|
Georgi Gerganov
|
05b06210c9
llama : more consistent names of count variables (#5994)
|
пре 1 година |
|
Georgi Gerganov
|
83796e62bc
llama : refactor unicode stuff (#5992)
|
пре 1 година |
 Jakub N
|
828defefb6
Update server docker image URLs (#5997)
|
пре 1 година |
|
Xuan Son Nguyen
|
caa106d4e0
Server: format error to json (#5961)
|
пре 1 година |
|
Michael Podvitskiy
|
3202361c5b
ggml, ci : Windows ARM runner and build fixes (#5979)
|
пре 1 година |
 Minsoo Cheong
|
332bdfd798
server : maintain chat completion id for streaming responses (#5988)
|
пре 1 година |
