Tags

Tags give the ability to mark specific points in history as being important

b1456

0e40806c · common : allow caller to handle help/argument exceptions (#3715) · Nov 01, 2023
b1455

a2758d08 · log : make generating separate log files optional (#3787) · Nov 01, 2023
b1454

e75dfdd3 · sampling : null grammar field after reset (#3885) · Nov 01, 2023
b1453

9a3b4f6c · ggml : fix UNUSED macro (#3762) · Nov 01, 2023
b1450

ca190bca · server : re-enable completion and embedded at the same time (#3876) · Nov 01, 2023
b1449

71e3718a · llama : refactor graph build code (#3837) · Nov 01, 2023
b1448

238657db · samplers : Min-P sampler implementation [alternative to Top P/Top K] (#3841) · Oct 31, 2023
b1446

207b5190 · ggml : move FP16 <-> FP32 code to ggml-impl.h (#3861) · Oct 30, 2023
b1445

6e08281e · Extend llama_kv_cache_seq_rm to allow matching any sequence (#3843) · Oct 29, 2023
b1444

2046eb43 · make : remove unnecessary dependency on build-info.h (#3842) · Oct 29, 2023
b1443

71a09da3 · llama : fix kv shift bug (#3835) · Oct 29, 2023
b1442

d69d777c · ggml : quantization refactoring (#3833) · Oct 29, 2023
b1440

82a6646e · metal : try cwd for ggml-metal.metal if bundle lookup fails (#3793) · Oct 28, 2023
b1437

bd6d9e20 · llama : allow quantizing k-quants to fall back when tensor size incompatible (#3747) · Oct 28, 2023
b1436

ee1a0ec9 · llama : add option for greedy sampling with probs (#3813) · Oct 28, 2023
b1435

17746110 · common : print that one line of the syntax help *also* to standard output (#3823) · Oct 28, 2023
b1434

fdee152e · starcoder : add GPU offloading (#3827) · Oct 28, 2023
b1433

41aee4df · speculative : ensure draft and target model vocab matches (#3812) · Oct 28, 2023
b1432

6d459cbf · llama : correctly report GGUFv3 format (#3818) · Oct 27, 2023
b1431

c8d6a1f3 · simple : fix batch handling (#3803) · Oct 27, 2023

Prev
1
…
48
49
50
51
52
53
54
55
56
…
99
Next