Skip to content

Releases: bartowski1182/llama.cpp

b2943

20 May 00:19
b442ab0
Compare
Choose a tag to compare
Merge branch 'ggerganov:master' into master

b2940

19 May 17:52
063b0d4
Compare
Choose a tag to compare
Merge branch 'ggerganov:master' into master

b2937

19 May 17:31
Compare
Choose a tag to compare
Add Smaug tokenizer support

b2936

19 May 17:28
5ca49cb
Compare
Choose a tag to compare
ggml: implement quantized KV cache for FA (#7372)