ReaDy: Recurrent States as Dynamic Context for Speculative Drafting in Hybrid Linear Attention Large Language Models
ReaDy uses recurrent states for speculative drafting, reaching 3.16× speedup on Qwen3.8-27B.
36
Organization
StartLuxLabs
- Mentions · 7d0
- Mentions · 30d2
- All mentions2
- First seenOct 13, 2026
- Last mentioned25d ago
Timeline
2 articles · newest firstReaDy uses HLA recurrent states to speed speculative decoding
On Qwen3.8-27B and one B200, ReaDy averages 3.16 times autoregressive speed and beats DSpark on every benchmark.
44
Appears with
- NVIDIAvendor · 2
- Qwen3.8-27Bai model · 2
- NVIDIA B200product · 2
- DSparkai model · 1
- ReaDyai model · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.