 Georgi Gerganov
|
2ee44c9a18
sync : ggml
|
пре 1 година |
|
Georgi Gerganov
|
6847d54c4f
tests : fix whitespace (#0)
|
пре 1 година |
 John Balis
|
fde13b3bb9
feat: cuda implementation for `ggml_conv_transpose_1d` (ggml/854)
|
пре 1 година |
 Kevin Wang
|
470939d483
common : preallocate sampling token data vector (#8363)
|
пре 1 година |
|
Georgi Gerganov
|
6f0dbf6ab0
infill : assert prefix/suffix tokens + remove old space logic (#8351)
|
пре 1 година |
|
Kevin Wang
|
ffd00797d8
common : avoid unnecessary logits fetch (#8358)
|
пре 1 година |
 toyer
|
04ce3a8b19
readme : add supported glm models (#8360)
|
пре 1 година |
 compilade
|
3fd62a6b1c
py : type-check all Python scripts with Pyright (#8341)
|
пре 1 година |
 Denis Spasyuk
|
a8db2a9ce6
Update llama-cli documentation (#8315)
|
пре 1 година |
 Alex Tuddenham
|
4090ea5501
ci : add checks for cmake,make and ctest in ci/run.sh (#8200)
|
пре 1 година |
 Andy Tai
|
f1948f1e10
readme : update bindings list (#8222)
|
пре 1 година |
 Brian
|
f7cab35ef9
gguf-hash: model wide and per tensor hashing using xxhash and sha1 (#8048)
|
пре 1 година |
|
toyer
|
905942abdb
llama : support glm3 and glm4 (#8031)
|
пре 1 година |
|
Georgi Gerganov
|
b5040086d4
llama : fix n_rot default (#8348)
|
пре 1 година |
|
compilade
|
d39130a398
py : use cpu-only torch in requirements.txt (#8335)
|
пре 1 година |
 standby24x7
|
b81ba1f96b
finetune: Rename command name in README.md (#8343)
|
пре 1 година |
|
standby24x7
|
210eb9ed0a
finetune: Rename an old command name in finetune.sh (#8344)
|
пре 1 година |
 Bjarke Viksøe
|
cb4d86c4d7
server: Retrieve prompt template in /props (#8337)
|
пре 1 година |
 Derrick T. Woolworth
|
86e7299ef5
added support for Authorization Bearer tokens when downloading model (#8307)
|
пре 1 година |
 Xuan Son Nguyen
|
60d83a0149
update main readme (#8333)
|
пре 1 година |
 Daniel Bevenius
|
87e25a1d1b
llama : add early return for empty range (#8327)
|
пре 1 година |
 jaime-m-p
|
213701b51a
Detokenizer fixes (#8039)
|
пре 1 година |
|
Xuan Son Nguyen
|
be20e7f49d
Reorganize documentation pages (#8325)
|
пре 1 година |
|
Georgi Gerganov
|
7ed03b8974
llama : fix compile warning (#8304)
|
пре 1 година |
 Natsu
|
1d894a790e
cmake : add GGML_BUILD and GGML_SHARED macro definitions (#8281)
|
пре 1 година |
 Ouadie EL FAROUKI
|
1f3e1b66e2
Enabled more data types for oneMKL gemm_batch (#8236)
|
пре 1 година |
|
Georgi Gerganov
|
148ec970b6
convert : remove AWQ remnants (#8320)
|
пре 1 година |
|
Georgi Gerganov
|
2cccbaa008
llama : minor indentation during tensor loading (#8304)
|
пре 1 година |
 Johannes Gäßler
|
8e558309dc
CUDA: MMQ support for iq4_nl, iq4_xs (#8278)
|
пре 1 година |
 Daniele
|
0a423800ff
CUDA: revert part of the RDNA1 optimizations (#8309)
|
пре 1 година |
