Admin message
为了安全，强烈建议开启2FA双因子认证：User Settings -> Account -> Enable two-factor authentication！！！
Tags
Tags give the ability to mark specific points in history as being important
b3537
725e3d94
·
quantize : update usage comment in quantize.cpp (#8889)
·
Aug 07, 2024
b3536
31958546
·
typo correction (#8891)
·
Aug 07, 2024
b3535
1e6f6554
·
server : add lora hotswap endpoint (WIP) (#8857)
·
Aug 06, 2024
b3534
641f5dd2
·
CUDA: fix padding logic for FP16/FP32 (#8884)
·
Aug 06, 2024
b3532
db20f50c
·
cmake : Link vulkan-shaders-gen with pthreads (#8835)
·
Aug 06, 2024
b3531
efda90c9
·
[Vulkan] Fix compilation of `vulkan-shaders-gen` on w64devkit after `
e31a4f67
` (#8880)
·
Aug 06, 2024
b3529
2d5dd7bb
·
ggml : add epsilon as a parameter for group_norm (#8818)
·
Aug 06, 2024
b3528
cdd1889d
·
convert : add support for XLMRoberta embedding models (#8658)
·
Aug 06, 2024
b3527
c21a8964
·
[CANN]: Fix ggml_backend_cann_buffer_get_tensor (#8871)
·
Aug 06, 2024
b3525
0a4ce786
·
common : Changed tuple to struct (TODO fix) (#8823)
·
Aug 05, 2024
b3524
bc0f887e
·
cann: fix buffer_num and runtime speed slowly error (#8865)
·
Aug 05, 2024
b3522
b9dfc25c
·
ggml : fix overflows in elu function (#8866)
·
Aug 05, 2024
b3520
d3f0c716
·
Stop the generation when <|eom_id|> token is encountered - needed for Llama...
·
Aug 05, 2024
b3519
e31a4f67
·
cmake: fix paths for vulkan shaders compilation on Windows (#8573)
·
Aug 05, 2024
b3518
400ae6f6
·
readme : update model list (#8851)
·
Aug 05, 2024
b3517
f1ea5146
·
llama : better replace_all (#8852)
·
Aug 05, 2024
b3516
064cdc26
·
vulkan : fix Qantized Mat-Vec Mul on AMD GPUs for ncols < 64 (#8855)
·
Aug 05, 2024
b3515
5587e57a
·
sync : ggml
·
Aug 05, 2024
b3512
c02b0a8a
·
cann: support q4_0 model (#8822)
·
Aug 05, 2024
b3511
0d6fb52b
·
Install curl in runtime layer (#8693)
·
Aug 04, 2024
1
…
60
61
62
63
64
65
66
67
68
…
178