Georgi Gerganov 3c6391e748 speculative-simple : free batch on exit (#17985) há 1 mês atrás
..
batched 6ab8eacddf examples : add -kvu to batched usage example [no ci] (#17469) há 2 meses atrás
batched.swift 29f538ac63 examples : remove references to `make` in examples [no ci] (#15457) há 5 meses atrás
convert-llama2c-to-ggml a81283820a gguf: gguf_writer refactor (#15691) há 4 meses atrás
deprecation-warning f112d198cd Update deprecation-warning.cpp (#10619) há 1 ano atrás
diffusion 4902eebe33 models : Added support for RND1 Diffusion Language Model (#17433) há 2 meses atrás
embedding e072b2052e ggml : add GGML_SCHED_NO_REALLOC option to disable reallocations in ggml_backend_sched (#17276) há 1 mês atrás
eval-callback 196f5083ef common : more accurate sampling timing (#17382) há 2 meses atrás
gen-docs 380b4c984e common: support negated args (#17919) há 1 mês atrás
gguf 5886f4f545 examples(gguf): GGUF example outputs (#17025) há 2 meses atrás
gguf-hash 53ff6b9b9f GGUF: C++ refactor, backend support, misc fixes (#11030) há 1 ano atrás
idle c41bde6fbd metal : add residency sets keep-alive heartbeat (#17766) há 1 mês atrás
llama.android 745aa5319b llama : deprecate llama_kv_self_ API (#14030) há 7 meses atrás
llama.swiftui 745aa5319b llama : deprecate llama_kv_self_ API (#14030) há 7 meses atrás
lookahead 2f37014073 lookahead : add sample command to readme (#15447) há 5 meses atrás
lookup 745aa5319b llama : deprecate llama_kv_self_ API (#14030) há 7 meses atrás
model-conversion fd1085ffb7 model-conversion : use CONVERTED_MODEL value for converted model [no ci] (#17984) há 1 mês atrás
parallel 2adf8d83ac parallel : add option for different RNG seeds (#14757) há 6 meses atrás
passkey 29f538ac63 examples : remove references to `make` in examples [no ci] (#15457) há 5 meses atrás
retrieval 29f538ac63 examples : remove references to `make` in examples [no ci] (#15457) há 5 meses atrás
save-load-state 8ce774a102 metal : fix build(#17799) há 1 mês atrás
simple 1cbd80f8cf examples : support encoder-decoder models in the simple example (#16002) há 4 meses atrás
simple-chat d7f5f4e578 simple-chat : fix context-exceeded condition (#14494) há 6 meses atrás
simple-cmake-pkg 817d743cc1 examples : add missing code block end marker [no ci] (#17756) há 1 mês atrás
speculative e92d53b29e sampling : optimize samplers by reusing bucket sort (#15665) há 4 meses atrás
speculative-simple 3c6391e748 speculative-simple : free batch on exit (#17985) há 1 mês atrás
sycl 7d2add51d8 sycl : support to malloc memory on device more than 4GB, update the doc and script (#17566) há 1 mês atrás
training 5cdb27e091 finetune: SGD optimizer, more CLI args (#13873) há 5 meses atrás
CMakeLists.txt c41bde6fbd metal : add residency sets keep-alive heartbeat (#17766) há 1 mês atrás
convert_legacy_llama.py a0ec17b32e metadata: Detailed Dataset Authorship Metadata (#8875) há 1 ano atrás
json_schema_pydantic_example.py 3fd62a6b1c py : type-check all Python scripts with Pyright (#8341) há 1 ano atrás
json_schema_to_grammar.py 0874693b44 common : fix json schema with '\' in literals (#17307) há 1 mês atrás
llama.vim 9ebebef62f llama : remove KV cache defragmentation logic (#15473) há 5 meses atrás
pydantic_models_to_grammar.py 090fca7a07 pydantic : replace uses of __annotations__ with get_type_hints (#8474) há 1 ano atrás
pydantic_models_to_grammar_examples.py 1d36b3670b llama : move end-user examples to tools directory (#13249) há 8 meses atrás
reason-act.sh e9b6350e61 scripts : make the shell scripts cross-platform (#14341) há 6 meses atrás
regex_to_grammar.py e235b267a2 py : switch to snake_case (#8305) há 1 ano atrás
server-llama2-13B.sh e9b6350e61 scripts : make the shell scripts cross-platform (#14341) há 6 meses atrás
server_embd.py a19b5cef16 llama : fix FA when KV cache is not used (i.e. embeddings) (#12825) há 9 meses atrás
ts-type-to-grammar.sh e9b6350e61 scripts : make the shell scripts cross-platform (#14341) há 6 meses atrás