Chen Xi
Chen Xi
@bdowling i agree with you as pyarrow has a good performance.
@lkk12014402 kaokao, please take a look on the new commit on measurement of ppl
Yes， it's still supported. Doc need to be updated, please wait the fix on how to use it.
https://github.com/intel/neural-speed/pull/224
> ### What happened? > Going through the manual - SYCL I mean. Everything compiles okay. Running it always thows an error. Can't make it work. OS used: Linux Gentoo....
https://github.com/ggerganov/llama.cpp/issues/9086 Refer to this issue for detailed design.
wait for habana team fix the issues: 1. https://jira.habana-labs.com/browse/SW-188060 2. https://jira.habana-labs.com/browse/SW-188059
> Hello, Thanks for the data! I am actually working on it now to reduce this part. I need to get the access to the H100 to test it. Hi,...
这个赞！我们有计划把replicate上collections里popular的那些都支持吗？
https://github.com/ggerganov/llama.cpp/pull/8554 @ch1y0q please refer this pr for fix of multi-device crash.