Juncheng Yang (@1a1a11a)

2026.10.07 22:24

The largest agentic LLM Inference dataset has arrived! 206B tokens · 12,002 sessions · 1,186,582 LLM requests · 1,213,347 tool calls The traces include tool names, arguments, durations, and more. Explore the dataset on @huggingface Paper coming soon! Stay tuned for more at

204

Forward to community

Juncheng Yang@1a1a11a

2026.09.20 00:34

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

1.2K

140

Forward to community

Juncheng Yang@1a1a11a

2026.09.16 23:04

Unpopular opinion—we should not publish system design papers any more (given that most papers have "untold story", instead, we should focus on (1) the problem (2) why the solution from AI does not work. How many disagree?