 slaren
|
652ca2bded
compare-llama-bench.py : remove mul_mat_q (#5892)
|
1 год назад |
 Jared Van Bortel
|
bd836944f8
quants : use MM256_SET_M128I consistently to fix gcc 7 build (#5889)
|
1 год назад |
 ExtReMLapin
|
3de31677d3
grammars : blacklists character control set (#5888)
|
1 год назад |
 Georgi Gerganov
|
82cb31eb93
Revert "grammars : don't allow to output unescaped new line in string (#5885)"
|
1 год назад |
|
ExtReMLapin
|
b1a4e994fd
grammars : don't allow to output unescaped new line in string (#5885)
|
1 год назад |
 0cc4m
|
61d1c88e15
Vulkan Improvements (#5835)
|
1 год назад |
 Neo Zhang Jianyu
|
21b0867433
[SYCL] fix mul_mat fault in CI/unit-test (#5862)
|
1 год назад |
 Minsoo Cheong
|
6a87ac3a52
fix editorconfig check break (#5879)
|
1 год назад |
 Jeffrey Quesnelle
|
29eee40474
fix speculative decoding build on windows (#5874)
|
1 год назад |
 hutli
|
1d41d6f7c2
nix: static build (#5814)
|
1 год назад |
|
Georgi Gerganov
|
29ae62d2ae
llama : fix embeddings (#5796)
|
1 год назад |
|
Georgi Gerganov
|
e0843afe1b
flake : fix
|
1 год назад |
|
Georgi Gerganov
|
a1c6d96ed8
ggml : fix unknown status (#0)
|
1 год назад |
|
Georgi Gerganov
|
efd8533ef8
sync : ggml
|
1 год назад |
 Michael Podvitskiy
|
9fa2627347
ggml : introduce ggml_status (ggml/750)
|
1 год назад |
 Dane Madsen
|
fe52be11e3
cmake : handle cases where git index is not found in .git (#5844)
|
1 год назад |
|
Minsoo Cheong
|
6d341ab6c5
speculative : implement stochastic speculative sampling (#5625)
|
1 год назад |
 Xuan Son Nguyen
|
4ffcdce2ff
add alias for chat template (#5858)
|
1 год назад |
|
Georgi Gerganov
|
a0fc62661f
sync : ggml
|
1 год назад |
 leejet
|
7d43c585dc
add some new ops, fix some operators and add batch operations to certain operators. (ggml/747)
|
1 год назад |
 DAN™
|
82f3e668ad
common : use LLAMA_DEFAULT_SEED (#5855)
|
1 год назад |
|
DAN™
|
5a51cc1bb4
main : support special tokens as reverse/anti prompt (#5847)
|
1 год назад |
|
slaren
|
67be2ce101
cuda : fix data race in soft max (#5853)
|
1 год назад |
|
Georgi Gerganov
|
231ae28f07
readme : add API changes section
|
1 год назад |
 Douglas Hanley
|
475df1d6cf
llama : allow for user specified embedding pooling type (#5849)
|
1 год назад |
 Nindaleth
|
87c2e8b279
gguf-dump : support i-quants (#5841)
|
1 год назад |
 compilade
|
de9692a7d2
llama : fix llama_copy_state_data with fragmented KV cache (#5840)
|
1 год назад |
 Pierrick Hymbert
|
e6029348e8
ci : schedule slow server tests only on Release or on demand (#5839)
|
1 год назад |
|
Pierrick Hymbert
|
8ef969afce
server : init http requests thread pool with --parallel if set (#5836)
|
1 год назад |
|
Georgi Gerganov
|
fa974646e1
flake.lock: Update (#5842)
|
1 год назад |
