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

b3936

9f45fc1e · llama : change warning to debug log · Oct 17, 2024
b3935

99bd4ac2 · llama : infill sampling handle very long tokens (#9924) · Oct 17, 2024
b3933

f010b77a · vulkan : add backend registry / device interfaces (#9721) · Oct 17, 2024
b3932

21942002 · fix: allocating CPU buffer with size `0` (#9917) · Oct 17, 2024
b3931

73afe681 · fix: use `vm_allocate` to allocate CPU backend buffer on macOS (#9875) · Oct 17, 2024
b3930

9e041024 · llama : suppress conversion from 'size_t' to 'int' (#9046) · Oct 16, 2024
b3928

66c2c930 · grammar : fix JSON Schema for string regex with top-level alt. (#9903) · Oct 16, 2024
b3927

10433e8b · llama : add tensor name for "result_norm" (#9907) · Oct 16, 2024
b3926

1f66b699 · server : fix the disappearance of the end of the text (#9867) · Oct 16, 2024
b3925

0e41b300 · sync : ggml · Oct 16, 2024
b3923

becfd387 · [CANN] Fix cann compilation error (#9891) · Oct 16, 2024
b3922

755a9b2b · llama : add infill sampler (#9896) · Oct 15, 2024
b3921

223c25a7 · server : improve infill context reuse (#9894) · Oct 15, 2024
b3920

fbc98b74 · sampling : add XTC sampler (#9742) · Oct 15, 2024
b3917

a89f75e1 · server : handle "logprobs" field with false value (#9871) · Oct 14, 2024
b3916

13dca2a5 · Vectorize load instructions in dmmv f16 CUDA kernel (#9816) · Oct 14, 2024
b3914

c7181bd2 · server : reuse cached context chunks (#9866) · Oct 13, 2024
b3912

edc26566 · server : add option to time limit the generation phase (#9865) · Oct 12, 2024
b3911

1bde94dd · server : remove self-extend features (#9860) · Oct 12, 2024
b3909

11ac9800 · llama : improve infill support and special token detection (#9798) · Oct 12, 2024

1
…
46
47
48
49
50
51
52
53
54
…
178