 Georgi Gerganov
|
2002bc96bf
server : refactor (#5882)
|
1 year ago |
 Neo Zhang Jianyu
|
ceca1aef07
[SYCL] fix error when set main gpu to non-zero (#5901)
|
1 year ago |
 Jared Van Bortel
|
e04e04f8fa
ggml : use SYS_get_cpu if SYS_getcpu is not defined (#5906)
|
1 year ago |
 bobqianic
|
e25fb4b18f
ggml : use `uint8x16_t` return type for `ggml_vqtbl1q_u8` (#5894)
|
1 year ago |
|
Georgi Gerganov
|
1e35d619a6
convert : remove AWQ remnants (#5768)
|
1 year ago |
|
Neo Zhang Jianyu
|
8ced9f7e32
add wait() to make code stable (#5895)
|
1 year ago |
 slaren
|
652ca2bded
compare-llama-bench.py : remove mul_mat_q (#5892)
|
1 year ago |
|
Jared Van Bortel
|
bd836944f8
quants : use MM256_SET_M128I consistently to fix gcc 7 build (#5889)
|
1 year ago |
 ExtReMLapin
|
3de31677d3
grammars : blacklists character control set (#5888)
|
1 year ago |
|
Georgi Gerganov
|
82cb31eb93
Revert "grammars : don't allow to output unescaped new line in string (#5885)"
|
1 year ago |
|
ExtReMLapin
|
b1a4e994fd
grammars : don't allow to output unescaped new line in string (#5885)
|
1 year ago |
 0cc4m
|
61d1c88e15
Vulkan Improvements (#5835)
|
1 year ago |
|
Neo Zhang Jianyu
|
21b0867433
[SYCL] fix mul_mat fault in CI/unit-test (#5862)
|
1 year ago |
 Minsoo Cheong
|
6a87ac3a52
fix editorconfig check break (#5879)
|
1 year ago |
 Jeffrey Quesnelle
|
29eee40474
fix speculative decoding build on windows (#5874)
|
1 year ago |
 hutli
|
1d41d6f7c2
nix: static build (#5814)
|
1 year ago |
|
Georgi Gerganov
|
29ae62d2ae
llama : fix embeddings (#5796)
|
1 year ago |
|
Georgi Gerganov
|
e0843afe1b
flake : fix
|
1 year ago |
|
Georgi Gerganov
|
a1c6d96ed8
ggml : fix unknown status (#0)
|
1 year ago |
|
Georgi Gerganov
|
efd8533ef8
sync : ggml
|
1 year ago |
 Michael Podvitskiy
|
9fa2627347
ggml : introduce ggml_status (ggml/750)
|
1 year ago |
 Dane Madsen
|
fe52be11e3
cmake : handle cases where git index is not found in .git (#5844)
|
1 year ago |
|
Minsoo Cheong
|
6d341ab6c5
speculative : implement stochastic speculative sampling (#5625)
|
1 year ago |
 Xuan Son Nguyen
|
4ffcdce2ff
add alias for chat template (#5858)
|
1 year ago |
|
Georgi Gerganov
|
a0fc62661f
sync : ggml
|
1 year ago |
 leejet
|
7d43c585dc
add some new ops, fix some operators and add batch operations to certain operators. (ggml/747)
|
1 year ago |
 DAN™
|
82f3e668ad
common : use LLAMA_DEFAULT_SEED (#5855)
|
1 year ago |
|
DAN™
|
5a51cc1bb4
main : support special tokens as reverse/anti prompt (#5847)
|
1 year ago |
|
slaren
|
67be2ce101
cuda : fix data race in soft max (#5853)
|
1 year ago |
|
Georgi Gerganov
|
231ae28f07
readme : add API changes section
|
1 year ago |
