vLLM releases DSpark draft model for Kimi K3.1 Pro speculative decoding
vLLM, Inferact, and Red Hat AI released DSpark, a 2.5B draft model for speculative decoding of Kimi K3.1 Pro, achieving GSM8K acceptance length of 5.57 and up to 30% longer acceptance with bounded draft KV cache.
2026-11-18 ~ 2026-11-19 · 3 related posts
- vLLM ships DSpark draft model for Kimi K3.1 Pro with up to 30% higher acceptance length — vllm_project · 2026-11-18
- Kimi K3.1 Pro DSpark model card: 2.5B draft, 5.57 acceptance length on GSM8K — vllm_project · 2026-11-18
1 near-duplicate retellings: AccBalanced