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
b3152
7b2f4a7d
·
[SYCL] remove global variables (#7710)
·
Jun 15, 2024
b3151
f8ec8877
·
ci : fix macos x86 build (#7940)
·
Jun 14, 2024
b3150
76d66ee0
·
CUDA: faster q2_K, q3_K MMQ + int8 tensor cores (#7921)
·
Jun 14, 2024
b3149
66ef1cee
·
metal : utilize max shared memory for mul_mat_id (#7935)
·
Jun 14, 2024
b3148
e65bbf60
·
llama-bench : fix RPC indication (#7936)
·
Jun 14, 2024
b3147
6fcd1331
·
llama : more checks before assuming FIM tokens (#7644)
·
Jun 14, 2024
b3146
41b9260f
·
convert : add Poro-34B-chat tokenizer support (#7713)
·
Jun 14, 2024
b3145
172c8256
·
rpc : fix ggml_backend_rpc_supports_buft() (#7918)
·
Jun 13, 2024
b3143
f578b86b
·
move BLAS to a separate backend (#6210)
·
Jun 13, 2024
b3141
96355290
·
CUDA: fix broken oob check for FA vec f32 kernel (#7904)
·
Jun 12, 2024
b3140
a9cae480
·
tests : add non-cont unary tests (#7857)
·
Jun 12, 2024
b3139
bfaa676b
·
ggml : improve ggml_is_contiguous logic (#7856)
·
Jun 12, 2024
b3138
704a35b1
·
server : restore numeric prompts (#7883)
·
Jun 12, 2024
b3135
73bac2b1
·
vulkan: select only one device for single gpu with multiple drivers (#7582)
·
Jun 11, 2024
b3134
ef52d1d1
·
Update Vulkan RoPE implementation (#7818)
·
Jun 11, 2024
b3131
148995e5
·
llama-bench: more compact markdown tables (#7879)
·
Jun 11, 2024
b3130
4bfe50f7
·
tests : check the Python version (#7872)
·
Jun 11, 2024
b3092
7d1a378b
·
CUDA: refactor mmq, dmmv, mmvq (#7716)
·
Jun 05, 2024
b3091
2b338967
·
ggml : refactor rope norm/neox (#7634)
·
Jun 05, 2024
b3089
c90dbe02
·
Fix per token atrributes bits (#7749)
·
Jun 05, 2024
1
…
73
74
75
76
77
78
79
80
81
…
178