 Georgi Gerganov
|
68265ebfc6
embedding : print all resulting embeddings (#899)
|
il y a 1 an |
|
Georgi Gerganov
|
381da2d9f0
metal : build metallib + fix embed path (#6015)
|
il y a 1 an |
|
Georgi Gerganov
|
0fd6c1f015
embedding : print cosine similarity (#899)
|
il y a 1 an |
 Linwei Wang
|
19885d205e
readme : update details about running llama in Termux on Android (#6039)
|
il y a 1 an |
|
Georgi Gerganov
|
76a936c893
readme : update API changes and hot topics
|
il y a 1 an |
 Clint Herron
|
463628372d
grammar : handle missing "root" node (#6004)
|
il y a 1 an |
 slaren
|
f30ea47a87
llama : add pipeline parallelism support (#6017)
|
il y a 1 an |
|
slaren
|
d8fd0ccf6a
test-backend-ops : skip CPU backend by default (#6028)
|
il y a 1 an |
 AidanBeltonS
|
b3d978600f
Update get version (#6025)
|
il y a 1 an |
 Xuan Son Nguyen
|
99b71c068f
Server: Use multi-task for embeddings endpoint (#6001)
|
il y a 1 an |
|
slaren
|
306d34be7a
ci : remove tidy-review (#6021)
|
il y a 1 an |
|
Georgi Gerganov
|
8030da7afe
ggml : reuse quantum structs across backends (#5943)
|
il y a 1 an |
|
Georgi Gerganov
|
184215e783
ggml : fix UB in IQ2_S and IQ3_S (#6012)
|
il y a 1 an |
|
Georgi Gerganov
|
48358b2e5b
sycl : update IQ1_S kernels (WIP - not working!) (#5995)
|
il y a 1 an |
 gliptic
|
5cdb371731
grammar : fix unnecessarily retained pointer to rules (#6003)
|
il y a 1 an |
 Kawrakow
|
44ca159faf
1.5 bit: we can do even better (#5999)
|
il y a 1 an |
|
Georgi Gerganov
|
05b06210c9
llama : more consistent names of count variables (#5994)
|
il y a 1 an |
|
Georgi Gerganov
|
83796e62bc
llama : refactor unicode stuff (#5992)
|
il y a 1 an |
 Jakub N
|
828defefb6
Update server docker image URLs (#5997)
|
il y a 1 an |
|
Xuan Son Nguyen
|
caa106d4e0
Server: format error to json (#5961)
|
il y a 1 an |
 Michael Podvitskiy
|
3202361c5b
ggml, ci : Windows ARM runner and build fixes (#5979)
|
il y a 1 an |
 Minsoo Cheong
|
332bdfd798
server : maintain chat completion id for streaming responses (#5988)
|
il y a 1 an |
 Gilad S
|
ecab1c75de
cmake : fix subdir for `LLAMA_METAL_EMBED_LIBRARY` (#5985)
|
il y a 1 an |
|
Georgi Gerganov
|
ee35600b90
llama : fix F16/F32 downcast + improve names (#5980)
|
il y a 1 an |
|
Kawrakow
|
be858f6205
Better 1.5 bit quantization (#5971)
|
il y a 1 an |
 Abhilash Majumder
|
ef3ced26a3
[SYCL] Add q3_s and q1_s (#5886)
|
il y a 1 an |
|
AidanBeltonS
|
3814a07392
[SYCL] Add support for SYCL Nvidia target (#5738)
|
il y a 1 an |
|
Georgi Gerganov
|
bb6d00bbf9
metal : move mm_id indices to shared mem (#5982)
|
il y a 1 an |
 Dean
|
7ab7b733bb
android : fix utf8 decoding error (#5935)
|
il y a 1 an |
|
Georgi Gerganov
|
d9f65c97c3
readme : update hot topics
|
il y a 1 an |
