Daniel Kleine 133c7b46b3 Fixed RNG seed docs (#9723) il y a 1 an
..
baby-llama 42c76d1358 Threadpool: take 2 (#8672) il y a 1 an
batched 6262d13e0b common : reimplement logging (#9418) il y a 1 an
batched-bench 6262d13e0b common : reimplement logging (#9418) il y a 1 an
batched.swift 0abc6a2c25 llama : llama_perf + option to disable timings during decode (#9355) il y a 1 an
convert-llama2c-to-ggml 6102037bbb vocab : refactor tokenizer to reduce init overhead (#9449) il y a 1 an
cvector-generator cad341d889 metal : reduce command encoding overhead (#9698) il y a 1 an
deprecation-warning be6d7c0791 examples : remove `finetune` and `train-text-from-scratch` (#8669) il y a 1 an
embedding f4d2b8846a llama : add reranking support (#9510) il y a 1 an
eval-callback 6262d13e0b common : reimplement logging (#9418) il y a 1 an
export-lora 6262d13e0b common : reimplement logging (#9418) il y a 1 an
gbnf-validator df270ef745 llama : refactor sampling v2 (#9294) il y a 1 an
gen-docs afbbfaa537 server : add more env vars, improve gen-docs (#9635) il y a 1 an
gguf 07283b1a90 gguf : handle null name during init (#8587) il y a 1 an
gguf-hash 1666f92dcd gguf-hash : update clib.json to point to original xxhash repo (#8491) il y a 1 an
gguf-split 76b37d1541 gguf-split : improve --split and --merge logic (#9619) il y a 1 an
gritlm 6262d13e0b common : reimplement logging (#9418) il y a 1 an
imatrix eca0fab44e imatrix : disable prompt escape by default (#9543) il y a 1 an
infill cea1486ecf log : add CONT level for continuing previous log entry (#9610) il y a 1 an
jeopardy 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) il y a 1 an
llama-bench 7be099fa81 llama-bench: correct argument parsing error message (#9524) il y a 1 an
llama.android 5fb5e24811 llama : minor sampling refactor (2) (#9386) il y a 1 an
llama.swiftui 5fb5e24811 llama : minor sampling refactor (2) (#9386) il y a 1 an
llava cad341d889 metal : reduce command encoding overhead (#9698) il y a 1 an
lookahead 6262d13e0b common : reimplement logging (#9418) il y a 1 an
lookup 6262d13e0b common : reimplement logging (#9418) il y a 1 an
main cea1486ecf log : add CONT level for continuing previous log entry (#9610) il y a 1 an
main-cmake-pkg 07a3fc0608 Removes multiple newlines at the end of files that is breaking the editorconfig step of CI. (#8258) il y a 1 an
parallel 6262d13e0b common : reimplement logging (#9418) il y a 1 an
passkey 6262d13e0b common : reimplement logging (#9418) il y a 1 an
perplexity 37f8c7b4c9 perplexity : remove extra new lines after chunks (#9596) il y a 1 an
quantize 63351143b2 quantize : improve type name parsing (#9570) il y a 1 an
quantize-stats df270ef745 llama : refactor sampling v2 (#9294) il y a 1 an
retrieval 6262d13e0b common : reimplement logging (#9418) il y a 1 an
rpc 841713e1e4 rpc : enable vulkan (#9714) il y a 1 an
save-load-state bfe76d4a17 common : move arg parser code to `arg.cpp` (#9388) il y a 1 an
server 133c7b46b3 Fixed RNG seed docs (#9723) il y a 1 an
simple 6262d13e0b common : reimplement logging (#9418) il y a 1 an
speculative b0f27361f3 sampling : avoid expensive softmax during greedy sampling (#9605) il y a 1 an
sycl faf67b3de4 [SYCL]set context default value to avoid memory issue, update guide (#9476) il y a 1 an
tokenize 6262d13e0b common : reimplement logging (#9418) il y a 1 an
CMakeLists.txt 148844fe97 examples : remove benchmark (#9704) il y a 1 an
Miku.sh 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) il y a 1 an
base-translate.sh 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) il y a 1 an
chat-13B.bat d9ad104440 Create chat-13B.bat (#592) il y a 2 ans
chat-13B.sh 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) il y a 1 an
chat-persistent.sh 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) il y a 1 an
chat-vicuna.sh 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) il y a 1 an
chat.sh 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) il y a 1 an
convert_legacy_llama.py 672a6f1018 convert-*.py: GGUF Naming Convention Refactor and Metadata Override Refactor (#7499) il y a 1 an
json_schema_pydantic_example.py 3fd62a6b1c py : type-check all Python scripts with Pyright (#8341) il y a 1 an
json_schema_to_grammar.py 3fd62a6b1c py : type-check all Python scripts with Pyright (#8341) il y a 1 an
llama.vim 125d03a503 llama.vim : added api key support (#5090) il y a 2 ans
llm.vim ad9ddcff6e llm.vim : stop generation at multiple linebreaks, bind to <F2> (#2879) il y a 2 ans
pydantic_models_to_grammar.py 090fca7a07 pydantic : replace uses of __annotations__ with get_type_hints (#8474) il y a 1 an
pydantic_models_to_grammar_examples.py 22f281aa16 examples : Rewrite pydantic_models_to_grammar_examples.py (#8493) il y a 1 an
reason-act.sh 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) il y a 1 an
regex_to_grammar.py e235b267a2 py : switch to snake_case (#8305) il y a 1 an
server-llama2-13B.sh 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) il y a 1 an
server_embd.py 3fd62a6b1c py : type-check all Python scripts with Pyright (#8341) il y a 1 an
ts-type-to-grammar.sh ab9a3240a9 JSON schema conversion: ⚡️ faster repetitions, min/maxLength for strings, cap number length (#6555) il y a 1 an