| .. |
|
batched-bench
|
147a521636
tool/ex/tests: consistently free ctx, then model (#18168)
|
1 개월 전 |
|
cli
|
2c1f199653
cli : fix reasoning responses in CLI (#18961)
|
1 주 전 |
|
completion
|
13f1e4a9ca
llama : add adaptive-p sampler (#17927)
|
2 주 전 |
|
cvector-generator
|
254098a279
common : refactor common_sampler + grammar logic changes (#17937)
|
1 개월 전 |
|
export-lora
|
07808ebb07
cmake : Do not install tools on iOS targets (#15903)
|
4 달 전 |
|
fit-params
|
64848deb18
llama-fit-params: free memory target per device (#18679)
|
3 주 전 |
|
gguf-split
|
6c2131773c
cli: new CLI experience (#17824)
|
1 개월 전 |
|
imatrix
|
254098a279
common : refactor common_sampler + grammar logic changes (#17937)
|
1 개월 전 |
|
llama-bench
|
aa1dc3770a
Setting mmap and direct_io to false as default in llama-bench.cpp (#18841)
|
2 주 전 |
|
mtmd
|
9eb5bfec1a
mtmd : update docs to use llama_model_n_embd_inp (#18999)
|
1 주 전 |
|
perplexity
|
254098a279
common : refactor common_sampler + grammar logic changes (#17937)
|
1 개월 전 |
|
quantize
|
33ded988ba
quantize: prevent input/output file collision (#18451)
|
1 개월 전 |
|
rpc
|
d2d626938a
Install rpc-server when GGML_RPC is ON. (#17149)
|
2 달 전 |
|
server
|
51fa458a92
server : support preserving reasoning_content in assistant message (#18994)
|
1 주 전 |
|
tokenize
|
07808ebb07
cmake : Do not install tools on iOS targets (#15903)
|
4 달 전 |
|
tts
|
516a4ca9b5
refactor : remove libcurl, use OpenSSL when available (#18828)
|
2 주 전 |
|
CMakeLists.txt
|
a180ba78c7
cmake: only build cli when server is enabled (#18670)
|
3 주 전 |
Xuan-Son Nguyen
51fa458a92
server : support preserving reasoning_content in assistant message (#18994)