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
b5200
c0a97b76
·
llama-bench : Add `--override-tensors` arg (#12922)
·
Apr 27, 2025
b5199
ced44be3
·
llama-chat : fix wrong template in GLM4-0414 (#13140)
·
Apr 27, 2025
b5198
e291450b
·
musa: fix build warning (#13129)
·
Apr 27, 2025
b5197
59e991c2
·
Fixes Qwen2.5VL segfault during inference with...
·
Apr 27, 2025
b5196
ca2bb89e
·
clip : Add Qwen2.5VL support (#12402)
·
Apr 27, 2025
b5195
2d451c80
·
common : add common_remote_get_content (#13123)
·
Apr 26, 2025
b5194
4753791e
·
clip : improve projector naming (#13118)
·
Apr 26, 2025
b5193
77d5e9a7
·
ggml: move fp16/bf16 conversion optimizations to CPU backend + export conversion APIs (#13107)
·
Apr 26, 2025
b5192
d5fe4e81
·
grammar : handle maxItems == 0 in JSON schema (#13117)
·
Apr 26, 2025
b5191
295354ea
·
llama : fix K-shift with quantized K and BLAS backend (#13113)
·
Apr 25, 2025
b5190
558a7647
·
Force FP32 compute in GLM4 FFN Down (#13101)
·
Apr 25, 2025
b5189
edb18b6e
·
clip : fix pixtral on some GPU backends (#13097)
·
Apr 25, 2025
b5188
514c4560
·
change the reorder tensor from init to execute OP (#13003)
·
Apr 25, 2025
b5187
553a5c3a
·
rpc : do not wait for response when sending RPC_CMD_SET_TENSOR (#12943)
·
Apr 25, 2025
b5186
13be08da
·
clip : remove boi/eoi embeddings for GLM-edge model (#13081)
·
Apr 24, 2025
b5185
226251ed
·
embeddings : fix batch sizes (#13076)
·
Apr 24, 2025
b5184
87616f06
·
ggml : fix trailing whitespaces (#0)
·
Apr 24, 2025
b5181
b10d8bfd
·
CUDA: use switch statements in constexpr functions (#13095)
·
Apr 24, 2025
b5180
13b45488
·
cmake : do not include ./src as public for libllama (#13062)
·
Apr 24, 2025
b5178
7c727fbe
·
arg : add --no-mmproj-offload (#13093)
·
Apr 24, 2025
1
…
3
4
5
6
7
8
9
10
11
…
178