Juncheng Yang
@1a1a11a
Assistant Professor at Harvard University, Ph.D @ CMU, ex-Snowflake, ex-AWS, ex-Twitter, ex-Cloudflare
加入 September 2014
2.1K 正在关注 2.9K 粉丝
Announcing one year of LLM inference metadata traces, with 6.12 billion requests.
We hope this dataset can support research on real-world LLM serving workload understanding, system design and infrastructure optimization. Explore the dataset and learn more:
Driven by our great graduate student William Nixon and
in collab with @jon_durbin @airesearch12 @chutes_ai
显示更多
