Sākums Izpētīt Palīdzība
Pierakstīties
cturan
/
llama.cpp
spogulis no https://github.com/cturan/llama.cpp
1
0
Atdalīts 0
Faili Problēmas 0 Vikivietne
Koks: 0c50923944
Atzari Tagi
llama.cpp
/
examples
Xuan-Son Nguyen 0c50923944 clip : use smart pointer (⚠️ breaking change) (#12869) 9 mēneši atpakaļ
..
batched 267c1399f1 common : refactor downloading system, handle mmproj with -hf option (#12694) 9 mēneši atpakaļ
batched-bench 267c1399f1 common : refactor downloading system, handle mmproj with -hf option (#12694) 9 mēneši atpakaļ
batched.swift e0dbec0bc6 llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181) 10 mēneši atpakaļ
convert-llama2c-to-ggml afa8a9ec9b llama : add `llama_vocab`, functions -> methods, naming (#11110) 1 gadu atpakaļ
cvector-generator e0dbec0bc6 llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181) 10 mēneši atpakaļ
deprecation-warning f112d198cd Update deprecation-warning.cpp (#10619) 1 gadu atpakaļ
embedding e0dbec0bc6 llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181) 10 mēneši atpakaļ
eval-callback afa8a9ec9b llama : add `llama_vocab`, functions -> methods, naming (#11110) 1 gadu atpakaļ
export-lora 267c1399f1 common : refactor downloading system, handle mmproj with -hf option (#12694) 9 mēneši atpakaļ
gbnf-validator 8b576b6c55 Tool call support (generic + native for Llama, Functionary, Hermes, Mistral, Firefunction, DeepSeek) w/ lazy grammars (#9639) 11 mēneši atpakaļ
gen-docs 7cc2d2c889 ggml : move AMX to the CPU backend (#10570) 1 gadu atpakaļ
gguf 53ff6b9b9f GGUF: C++ refactor, backend support, misc fixes (#11030) 1 gadu atpakaļ
gguf-hash 53ff6b9b9f GGUF: C++ refactor, backend support, misc fixes (#11030) 1 gadu atpakaļ
gguf-split 23106f94ea gguf-split : --merge now respects --dry-run option (#12681) 9 mēneši atpakaļ
gritlm 267c1399f1 common : refactor downloading system, handle mmproj with -hf option (#12694) 9 mēneši atpakaļ
imatrix e0dbec0bc6 llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181) 10 mēneši atpakaļ
infill e0dbec0bc6 llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181) 10 mēneši atpakaļ
jeopardy 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 1 gadu atpakaļ
llama-bench e0dbec0bc6 llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181) 10 mēneši atpakaļ
llama.android bd3f59f812 cmake : enable curl by default (#12761) 9 mēneši atpakaļ
llama.swiftui e0dbec0bc6 llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181) 10 mēneši atpakaļ
llava 0c50923944 clip : use smart pointer (⚠️ breaking change) (#12869) 9 mēneši atpakaļ
lookahead e0dbec0bc6 llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181) 10 mēneši atpakaļ
lookup e0dbec0bc6 llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181) 10 mēneši atpakaļ
main 60c902926c docs : bring llama-cli conversation/template docs up-to-date (#12426) 10 mēneši atpakaļ
parallel a10b36c91a llama : refactor kv cache guard (#12695) 9 mēneši atpakaļ
passkey 267c1399f1 common : refactor downloading system, handle mmproj with -hf option (#12694) 9 mēneši atpakaļ
perplexity 4ccea213bc hellaswag: display estimated score confidence interval (#12797) 9 mēneši atpakaļ
quantize 5bbe6a9fe9 ggml : portability fixes for VS 2017 (#12150) 10 mēneši atpakaļ
quantize-stats e0dbec0bc6 llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181) 10 mēneši atpakaļ
retrieval e0dbec0bc6 llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181) 10 mēneši atpakaļ
rpc ef03229ff4 rpc : update README for cache usage (#12620) 9 mēneši atpakaļ
run bd3f59f812 cmake : enable curl by default (#12761) 9 mēneši atpakaļ
save-load-state e0dbec0bc6 llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181) 10 mēneši atpakaļ
server 381603a775 ci: detach common from the library (#12827) 9 mēneši atpakaļ
simple afa8a9ec9b llama : add `llama_vocab`, functions -> methods, naming (#11110) 1 gadu atpakaļ
simple-chat e0dbec0bc6 llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181) 10 mēneši atpakaļ
simple-cmake-pkg 68ff663a04 repo : update links to new url (#11886) 11 mēneši atpakaļ
speculative 267c1399f1 common : refactor downloading system, handle mmproj with -hf option (#12694) 9 mēneši atpakaļ
speculative-simple 267c1399f1 common : refactor downloading system, handle mmproj with -hf option (#12694) 9 mēneši atpakaļ
sycl bd3f59f812 cmake : enable curl by default (#12761) 9 mēneši atpakaļ
tokenize afa8a9ec9b llama : add `llama_vocab`, functions -> methods, naming (#11110) 1 gadu atpakaļ
tts 267c1399f1 common : refactor downloading system, handle mmproj with -hf option (#12694) 9 mēneši atpakaļ
CMakeLists.txt 0bf2d10c55 tts : add OuteTTS support (#10784) 1 gadu atpakaļ
Miku.sh 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 1 gadu atpakaļ
chat-13B.bat d9ad104440 Create chat-13B.bat (#592) 2 gadi atpakaļ
chat-13B.sh 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 1 gadu atpakaļ
chat-persistent.sh 8fc393f246 scripts : fix pattern and get n_tokens in one go (#10221) 1 gadu atpakaļ
chat-vicuna.sh 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 1 gadu atpakaļ
chat.sh 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 1 gadu atpakaļ
convert_legacy_llama.py a0ec17b32e metadata: Detailed Dataset Authorship Metadata (#8875) 1 gadu atpakaļ
json_schema_pydantic_example.py 3fd62a6b1c py : type-check all Python scripts with Pyright (#8341) 1 gadu atpakaļ
json_schema_to_grammar.py 669912d9a5 `tool-call`: fix Qwen 2.5 Coder support, add micro benchmarks, support trigger patterns for lazy grammars (#12034) 10 mēneši atpakaļ
llama.vim 68ff663a04 repo : update links to new url (#11886) 11 mēneši atpakaļ
llm.vim ad9ddcff6e llm.vim : stop generation at multiple linebreaks, bind to <F2> (#2879) 2 gadi atpakaļ
pydantic_models_to_grammar.py 090fca7a07 pydantic : replace uses of __annotations__ with get_type_hints (#8474) 1 gadu atpakaļ
pydantic_models_to_grammar_examples.py 68ff663a04 repo : update links to new url (#11886) 11 mēneši atpakaļ
reason-act.sh 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 1 gadu atpakaļ
regex_to_grammar.py e235b267a2 py : switch to snake_case (#8305) 1 gadu atpakaļ
server-llama2-13B.sh 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 1 gadu atpakaļ
server_embd.py a19b5cef16 llama : fix FA when KV cache is not used (i.e. embeddings) (#12825) 9 mēneši atpakaļ
ts-type-to-grammar.sh ab9a3240a9 JSON schema conversion: ⚡️ faster repetitions, min/maxLength for strings, cap number length (#6555) 1 gadu atpakaļ