inference 9
- A Request's Life in vLLM V1
- Anatomy of an LLM Serving Engine
- Heterogeneity Moved Inside the Chip
- The Illusion of Determinism in Disaggregated Inference
- A Cache Its Own Prefill Would Never Have Produced
- Two Schedulers, One SLO
- There Is No Address
- The KV Cache Has No ABI
- Prefill and Decode Want Different Computers