hangfu-guo

Benchmarking Chatglm3-6B on Xeon SPR: Forward() expected at most 5 arguments but received 6

1

Issue happens during benchingmarking ChatGLm3-6B, using run-spr.sh and config test_api as bigdl_ipex_int4. **Environment:**] pip install --pre --upgrade ipex-llm[all] && \ # Fix CVE-2024-22195 pip install Jinja2==3.1.3 && \ pip install...

Hi, appreciate this benchmark tool! Just wondering if the results utilize the latest AI acceleration techs in different products. Since I saw the FLOPS/OPS could be much lower than what...