Skip to content
GitLab
Explore
Sign in
Tags
Tags give the ability to mark specific points in history as being important
b2420
3fe8d7a1
·
ggml : designate enum vals for integer types (#6050)
·
Mar 14, 2024
b2419
68265ebf
·
embedding : print all resulting embeddings (#899)
·
Mar 14, 2024
b2418
381da2d9
·
metal : build metallib + fix embed path (#6015)
·
Mar 14, 2024
b2417
0fd6c1f0
·
embedding : print cosine similarity (#899)
·
Mar 14, 2024
b2414
46362837
·
grammar : handle missing "root" node (#6004)
·
Mar 13, 2024
b2413
f30ea47a
·
llama : add pipeline parallelism support (#6017)
·
Mar 13, 2024
b2412
d8fd0ccf
·
test-backend-ops : skip CPU backend by default (#6028)
·
Mar 13, 2024
b2411
b3d97860
·
Update get version (#6025)
·
Mar 13, 2024
b2410
99b71c06
·
Server: Use multi-task for embeddings endpoint (#6001)
·
Mar 13, 2024
b2409
306d34be
·
ci : remove tidy-review (#6021)
·
Mar 12, 2024
b2408
8030da7a
·
ggml : reuse quantum structs across backends (#5943)
·
Mar 12, 2024
b2407
184215e7
·
ggml : fix UB in IQ2_S and IQ3_S (#6012)
·
Mar 12, 2024
b2406
48358b2e
·
sycl : update IQ1_S kernels (WIP - not working!) (#5995)
·
Mar 12, 2024
b2405
5cdb3717
·
grammar : fix unnecessarily retained pointer to rules (#6003)
·
Mar 11, 2024
b2404
44ca159f
·
1.5 bit: we can do even better (#5999)
·
Mar 11, 2024
b2403
05b06210
·
llama : more consistent names of count variables (#5994)
·
Mar 11, 2024
b2402
83796e62
·
llama : refactor unicode stuff (#5992)
·
Mar 11, 2024
b2400
caa106d4
·
Server: format error to json (#5961)
·
Mar 11, 2024
b2399
3202361c
·
ggml, ci : Windows ARM runner and build fixes (#5979)
·
Mar 11, 2024
b2398
332bdfd7
·
server : maintain chat completion id for streaming responses (#5988)
·
Mar 11, 2024
Prev
1
…
16
17
18
19
20
21
22
23
24
…
99
Next