AI & ML
Callo: Serving Cache-Miss Requests with Speculative Decoding on Invalidated KV under Prefill-Decode Disaggregation
arXiv cs.DC0 views
arXiv:2611.18459v1 Announce Type: new Abstract: Agent sessions may involve frequent context edits, which effectively invalidate cached KV state and force requests to wait for re-prefill before decoding. We present Callo, a disaggregated serving system that leverages invalidated KV for speculative drafts to reduce this latency, while verifying drafts against the exact KV after prefill before committing tokens. Callo makes effective use of decode resources by scheduling speculations during periods of underutilization and preempting speculations when drafts are likely to not be accepted. We evaluated Callo on a two-GPU testbed using SWE-agent sessions across three model families, observing all-request speedups of 1.05-1.19x over vLLM at moderate load. We demonstrate that these gains are also realized at scale through cluster-level simulations driven by real-world traces.
Source:https://arxiv.org/abs/2611.18459PreviousBPU-SpikeMM:Exact Matrix Multiplication via Spatio-Temporal Spike Encoding on Real Neuromorphic HardwareNextAscendGYM: A Cost-Aware Kernel Optimization Benchmark for Real-World Workloads on Ascend NPUs
Related posts
In which John becomes a Machine Learning researcher
0Hacker News New
Can We Fix AI?
0Hacker News New
I'm Glad That Literary Awards Are Going to AI
0Hacker News New
Show HN: TalentRadar – 3D geospatial tech compensation and role radar
0Hacker News Show
Show HN: Brief2mp4 – ClaudeCode/Codex skill that checks videos against the brief
0Hacker News Show
Show HN: Figma Like AI Landing Page Builder
0Hacker News Show