Tags

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

b2450

d01b3c4c · common: llama_load_model_from_url using --model-url (#6098) · Mar 17, 2024
b2449

cd776c37 · ci : close all stale issues at once (#6115) · Mar 17, 2024
b2448

dc0f6125 · ggml:fix finding transfer queue family index error (#6094) · Mar 17, 2024
b2447

c47cf414 · ggml : add AVX512F SIMD (#6088) · Mar 16, 2024
b2444

15961ec0 · common : refactor nested if causing error C1061 on MSVC (#6101) · Mar 16, 2024
b2440

12247f4c · llama : add Command-R support (#6033) · Mar 15, 2024
b2439

4e9a7f7f · llava : change API to pure C style for Rust FFI bindgen (#6079) · Mar 15, 2024
b2438

3020327f · cuda : disable unused cudaLaunchHostFunc code (#6078) · Mar 15, 2024
b2437

46acb367 · fix set main gpu error (#6073) · Mar 15, 2024
b2436

131b0584 · make : ggml-metal.o depends on ggml.h · Mar 15, 2024
b2435

753e36f6 · [SYCL] Fix non-intel device selection (#6042) · Mar 15, 2024
b2434

7ce2c77f · gguf : add support for I64 and F64 arrays (#6062) · Mar 15, 2024
b2433

aab606a1 · llama : add Orion chat template (#6066) · Mar 15, 2024
b2432

b0bc9f4a · llama-bench : use random tokens to improve accuracy with mixtral (#6069) · Mar 15, 2024
b2430

6e0438da · gguf : fix resource leaks (#6061) · Mar 14, 2024
b2428

69ff6139 · llama : support models without vocabulary (#5798) · Mar 14, 2024
b2427

044ec4b2 · embedding : add EOS token if not present (#899) · Mar 14, 2024
b2424

43241adf · server: disable debug release type sanitizer, simplify trigger (#6047) · Mar 14, 2024
b2423

a44bc969 · llama : fix typo · Mar 14, 2024
b2422

2c4fb692 · llama : optimize defrag moves + fix fragmentation calculation (#6037) · Mar 14, 2024

Prev
1
…
15
16
17
18
19
20
21
22
23
…
99
Next