Xuan Son Nguyen 6e7d133a5f server : refactor multitask handling (#9274) пре 1 година
..
baby-llama 42c76d1358 Threadpool: take 2 (#8672) пре 1 година
batched da3913d8f9 batched: fix n_predict parameter (#8527) пре 1 година
batched-bench ecf6b7f23e batched-bench : handle empty `-npl` (#8839) пре 1 година
batched.swift 213701b51a Detokenizer fixes (#8039) пре 1 година
benchmark 42c76d1358 Threadpool: take 2 (#8672) пре 1 година
convert-llama2c-to-ggml 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) пре 1 година
cvector-generator 42c76d1358 Threadpool: take 2 (#8672) пре 1 година
deprecation-warning be6d7c0791 examples : remove `finetune` and `train-text-from-scratch` (#8669) пре 1 година
embedding 7c3f55c100 Add support for encoder-only T5 models (#8900) пре 1 година
eval-callback 4af8420afb common : remove duplicate function llama_should_add_bos_token (#8778) пре 1 година
export-lora 42c76d1358 Threadpool: take 2 (#8672) пре 1 година
gbnf-validator 938943cdbf llama : move vocab, grammar and sampling into separate files (#8508) пре 1 година
gguf 07283b1a90 gguf : handle null name during init (#8587) пре 1 година
gguf-hash 1666f92dcd gguf-hash : update clib.json to point to original xxhash repo (#8491) пре 1 година
gguf-split 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) пре 1 година
gritlm 80ea089d77 llama : allow pooled embeddings on any model (#7477) пре 1 година
imatrix 4af8420afb common : remove duplicate function llama_should_add_bos_token (#8778) пре 1 година
infill 4af8420afb common : remove duplicate function llama_should_add_bos_token (#8778) пре 1 година
jeopardy 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) пре 1 година
llama-bench 42c76d1358 Threadpool: take 2 (#8672) пре 1 година
llama.android b7c11d36e6 examples: fix android example cannot be generated continuously (#8621) пре 1 година
llama.swiftui 42c76d1358 Threadpool: take 2 (#8672) пре 1 година
llava 7ea8d80d53 llava : the function "clip" should be int (#9237) пре 1 година
lookahead 0a4ce78681 common : Changed tuple to struct (TODO fix) (#8823) пре 1 година
lookup 0a4ce78681 common : Changed tuple to struct (TODO fix) (#8823) пре 1 година
main b60074f1c2 llama-cli : remove duplicated log message (#9275) пре 1 година
main-cmake-pkg 07a3fc0608 Removes multiple newlines at the end of files that is breaking the editorconfig step of CI. (#8258) пре 1 година
parallel 0a4ce78681 common : Changed tuple to struct (TODO fix) (#8823) пре 1 година
passkey 61ecafa390 passkey : add short intro to README.md [no-ci] (#8317) пре 1 година
perplexity 4af8420afb common : remove duplicate function llama_should_add_bos_token (#8778) пре 1 година
quantize 8f824ffe8e quantize : fix typo in usage help of `quantize.cpp` (#9145) пре 1 година
quantize-stats 370b1f7e7a ggml : minor naming changes (#8433) пре 1 година
retrieval 4b9afbbe90 retrieval : fix memory leak in retrieval query handling (#8955) пре 1 година
rpc b72942fac9 Merge commit from fork пре 1 година
save-load-state 0a4ce78681 common : Changed tuple to struct (TODO fix) (#8823) пре 1 година
server 6e7d133a5f server : refactor multitask handling (#9274) пре 1 година
simple 5f4dcb1e60 simple : update name of executable to llama-simple (#8885) пре 1 година
speculative 42c76d1358 Threadpool: take 2 (#8672) пре 1 година
sycl 0478174d59 [SYCL] Updated SYCL device filtering (#8901) пре 1 година
tokenize 4af8420afb common : remove duplicate function llama_should_add_bos_token (#8778) пре 1 година
CMakeLists.txt be6d7c0791 examples : remove `finetune` and `train-text-from-scratch` (#8669) пре 1 година
Miku.sh 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) пре 1 година
base-translate.sh 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) пре 1 година
chat-13B.bat d9ad104440 Create chat-13B.bat (#592) пре 2 година
chat-13B.sh 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) пре 1 година
chat-persistent.sh 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) пре 1 година
chat-vicuna.sh 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) пре 1 година
chat.sh 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) пре 1 година
convert_legacy_llama.py 672a6f1018 convert-*.py: GGUF Naming Convention Refactor and Metadata Override Refactor (#7499) пре 1 година
json_schema_pydantic_example.py 3fd62a6b1c py : type-check all Python scripts with Pyright (#8341) пре 1 година
json_schema_to_grammar.py 3fd62a6b1c py : type-check all Python scripts with Pyright (#8341) пре 1 година
llama.vim 125d03a503 llama.vim : added api key support (#5090) пре 2 година
llm.vim ad9ddcff6e llm.vim : stop generation at multiple linebreaks, bind to <F2> (#2879) пре 2 година
pydantic_models_to_grammar.py 090fca7a07 pydantic : replace uses of __annotations__ with get_type_hints (#8474) пре 1 година
pydantic_models_to_grammar_examples.py 22f281aa16 examples : Rewrite pydantic_models_to_grammar_examples.py (#8493) пре 1 година
reason-act.sh 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) пре 1 година
regex_to_grammar.py e235b267a2 py : switch to snake_case (#8305) пре 1 година
server-llama2-13B.sh 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) пре 1 година
server_embd.py 3fd62a6b1c py : type-check all Python scripts with Pyright (#8341) пре 1 година
ts-type-to-grammar.sh ab9a3240a9 JSON schema conversion: ⚡️ faster repetitions, min/maxLength for strings, cap number length (#6555) пре 1 година