I’m a little surprised by the mention of chatcode.py which was merged into chat.py almost two months ago. Also it doesn’t really require flash-attn-2 to run “properly”, it just runs a little better that way. But it’s perfectly usable without it.
Thanks for your excellent library! It makes sense because I started writing this article about two months ago (chatcode.py is still mentioned in the README.md by the way). I had a very low throughput using ExLlamaV2 without flash-attn-2. Do you know if it’s still the case? I updated these two points, thanks for your feedback.
I’m a little surprised by the mention of
chatcode.py
which was merged intochat.py
almost two months ago. Also it doesn’t really require flash-attn-2 to run “properly”, it just runs a little better that way. But it’s perfectly usable without it.Great article, though. thanks. :)
Thanks for your excellent library! It makes sense because I started writing this article about two months ago (
chatcode.py
is still mentioned in theREADME.md
by the way). I had a very low throughput using ExLlamaV2 without flash-attn-2. Do you know if it’s still the case? I updated these two points, thanks for your feedback.