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

b2669

e689fc4e · [bug fix] convert github repository_owner to lowercase (#6673) · Apr 14, 2024
b2667

de17e3f7 · fix memcpy() crash, add missed cmd in guide, fix softmax (#6622) · Apr 14, 2024
b2666

b5e7285b · CUDA: fix matrix multiplication logic for tests (#6667) · Apr 14, 2024
b2665

4bd0f93e · model: support arch `DbrxForCausalLM` (#6515) · Apr 13, 2024
b2664

ab9a3240 · JSON schema conversion: ⚡ faster repetitions, min/maxLength for strings, cap number length (#6555) · Apr 12, 2024
b2663

fbbc030b · metal : unify mul_mv_id kernels (#6556) · Apr 12, 2024
b2661

24ee66ed · server : coherent log output for KV cache full (#6637) · Apr 12, 2024
b2660

91c73601 · llama : add gguf_remove_key + remove split meta during quantize (#6591) · Apr 12, 2024
b2658

ef21ce4c · imatrix : remove invalid assert (#6632) · Apr 12, 2024
b2657

dee7f8d6 · Correct free memory and total memory. (#6630) · Apr 12, 2024
b2656

81da18e7 · eval-callback: use ggml_op_desc to pretty print unary operator name (#6631) · Apr 12, 2024
b2655

9ed2737a · ci : disable Metal for macOS-latest-cmake-x64 (#6628) · Apr 12, 2024
b2647

8228b66d · gguf : add option to not check tensor data (#6582) · Apr 10, 2024
b2646

b3a96f27 · minor layout improvements (#6572) · Apr 10, 2024
b2645

4f407a0a · llama : add model types for mixtral (#6589) · Apr 10, 2024
b2638

c4a3a4ff · sync : ggml · Apr 09, 2024
b2636

5dc9dd71 · llama : add Command R Plus support (#6491) · Apr 09, 2024
b2633

cecd8d3c · Comment explaining a decision (#6531) · Apr 08, 2024
b2632

b73e564b · quantize : fix precedence of cli args (#6541) · Apr 08, 2024
b2630

beea6e1b · llama : save and restore kv cache for single seq id (#6341) · Apr 08, 2024

1
…
88
89
90
91
92
93
94
95
96
…
178