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

b1993

9241c3a2 · Apply min_p to unsorted tokens (#5115) · Jan 28, 2024
b1992

b2b2bf98 · Tests for min_p, sampling queue (#5147) · Jan 28, 2024
b1990

f2e69d28 · llama : add support for Orion-14B (#5118) · Jan 28, 2024
b1989

39baaf55 · docker : add server-first container images (#5157) · Jan 28, 2024
b1988

6db2b41a · llava : support for Yi-VL and fix for mobileVLM (#5093) · Jan 27, 2024
b1987

753eafed · sync : ggml · Jan 27, 2024
b1985

35a2ee91 · Remove unused data and add fixes (#5154) · Jan 27, 2024
b1984

ec903c03 · server : add self-extend support (#5104) · Jan 27, 2024
b1983

a1d6df12 · Add OpenCL add kernel (#5151) · Jan 26, 2024
b1982

bbe7c56c · cmake : pass CPU architecture flags to nvcc (#5146) · Jan 26, 2024
b1981

62fead3e · cuda : fix tensor size calculation for non-split buffer (#5145) · Jan 26, 2024
b1980

15b4538f · ggml-alloc : add 10% margin to the buffer sizes (#5149) · Jan 26, 2024
b1979

7032f4f6 · ggml : update softmax n_task calculation (#5126) · Jan 26, 2024
b1976

48c857aa · server : refactored the task processing logic (#5065) · Jan 26, 2024
b1975

413e7b05 · ci : add model tests + script wrapper (#4586) · Jan 26, 2024
b1974

6dd3c28c · metal : remove unused `n_buffers` and `buffers` (#5129) · Jan 26, 2024
b1971

1182cf4d · Another bucket sort (#5109) · Jan 26, 2024
b1969

5eaf9964 · llama : dynamic temperature sampling (#4972) · Jan 25, 2024
b1966

faa3526a · Fix Q3_K_XS for MoE models (#5113) · Jan 25, 2024
b1965

ddc5a503 · metal : show compile log messages · Jan 25, 2024