| .. |
|
batched-bench
|
147a521636
tool/ex/tests: consistently free ctx, then model (#18168)
|
1 month ago |
|
cli
|
ce3bf9b1a4
server: update docs for sleeping [no ci] (#18777)
|
2 weeks ago |
|
completion
|
ce3bf9b1a4
server: update docs for sleeping [no ci] (#18777)
|
2 weeks ago |
|
cvector-generator
|
254098a279
common : refactor common_sampler + grammar logic changes (#17937)
|
1 month ago |
|
export-lora
|
07808ebb07
cmake : Do not install tools on iOS targets (#15903)
|
4 months ago |
|
fit-params
|
64848deb18
llama-fit-params: free memory target per device (#18679)
|
3 weeks ago |
|
gguf-split
|
6c2131773c
cli: new CLI experience (#17824)
|
1 month ago |
|
imatrix
|
254098a279
common : refactor common_sampler + grammar logic changes (#17937)
|
1 month ago |
|
llama-bench
|
db79dc06b1
llama-bench: add direct_io parameter (#18778)
|
2 weeks ago |
|
mtmd
|
d98b548120
Restore clip's cb() to its rightful glory - extract common debugging elements in llama (#17914)
|
2 weeks ago |
|
perplexity
|
254098a279
common : refactor common_sampler + grammar logic changes (#17937)
|
1 month ago |
|
quantize
|
33ded988ba
quantize: prevent input/output file collision (#18451)
|
4 weeks ago |
|
rpc
|
d2d626938a
Install rpc-server when GGML_RPC is ON. (#17149)
|
2 months ago |
|
server
|
39173bcacb
context : reserve new scheduler when graph topology changes (#18547)
|
2 weeks ago |
|
tokenize
|
07808ebb07
cmake : Do not install tools on iOS targets (#15903)
|
4 months ago |
|
tts
|
516a4ca9b5
refactor : remove libcurl, use OpenSSL when available (#18828)
|
2 weeks ago |
|
CMakeLists.txt
|
a180ba78c7
cmake: only build cli when server is enabled (#18670)
|
2 weeks ago |
Georgi Gerganov
39173bcacb
context : reserve new scheduler when graph topology changes (#18547)