Skip to content
GitLab
Explore
Sign in
Tags
Tags give the ability to mark specific points in history as being important
b1999
d2f650cb
·
metal : free metal objects (#5161)
·
Jan 28, 2024
b1998
35dec26c
·
sync : ggml
·
Jan 28, 2024
b1996
2307523d
·
ggml : add Vulkan backend (#2059)
·
Jan 28, 2024
b1995
0f648573
·
ggml : add unified SYCL backend for Intel GPUs (#2690)
·
Jan 28, 2024
b1993
9241c3a2
·
Apply min_p to unsorted tokens (#5115)
·
Jan 28, 2024
b1992
b2b2bf98
·
Tests for min_p, sampling queue (#5147)
·
Jan 28, 2024
b1990
f2e69d28
·
llama : add support for Orion-14B (#5118)
·
Jan 28, 2024
b1989
39baaf55
·
docker : add server-first container images (#5157)
·
Jan 28, 2024
b1988
6db2b41a
·
llava : support for Yi-VL and fix for mobileVLM (#5093)
·
Jan 27, 2024
b1987
753eafed
·
sync : ggml
·
Jan 27, 2024
b1985
35a2ee91
·
Remove unused data and add fixes (#5154)
·
Jan 27, 2024
b1984
ec903c03
·
server : add self-extend support (#5104)
·
Jan 27, 2024
b1983
a1d6df12
·
Add OpenCL add kernel (#5151)
·
Jan 26, 2024
b1982
bbe7c56c
·
cmake : pass CPU architecture flags to nvcc (#5146)
·
Jan 26, 2024
b1981
62fead3e
·
cuda : fix tensor size calculation for non-split buffer (#5145)
·
Jan 26, 2024
b1980
15b4538f
·
ggml-alloc : add 10% margin to the buffer sizes (#5149)
·
Jan 26, 2024
b1979
7032f4f6
·
ggml : update softmax n_task calculation (#5126)
·
Jan 26, 2024
b1976
48c857aa
·
server : refactored the task processing logic (#5065)
·
Jan 26, 2024
b1975
413e7b05
·
ci : add model tests + script wrapper (#4586)
·
Jan 26, 2024
b1974
6dd3c28c
·
metal : remove unused `n_buffers` and `buffers` (#5129)
·
Jan 26, 2024
Prev
1
…
30
31
32
33
34
35
36
37
38
…
99
Next