ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1
ipex-llm/python
History
Yishuo Wang bfd9f88f0d [LLM] Use fp32 as dtype when batch_size <=8 and qtype is q4_0/q8_0/fp8 (#9365)
2023-11-08 09:54:53 +08:00
..
llm [LLM] Use fp32 as dtype when batch_size <=8 and qtype is q4_0/q8_0/fp8 (#9365) 2023-11-08 09:54:53 +08:00