Show HN: Resin, fast native scheduler for LLM inference engines
Opens the thread with a scheduling-layer approach to faster serving.
AI Storyline
3 items · 2 sources · 3 days
Operational story trace
Fast Inference
Follow in this browser to see new updates on your Live feed.
Latest change
Warmctl, a new open-source tool shared on Show HN, targets slow cold starts for vLLM servers, adding a startup-latency fix to a thread about scheduling and local serving.
Earlier contextThe story so far
This is a loose cluster of three unrelated projects that share one goal: serving LLMs faster below the model layer. It began with Resin, a native scheduler for inference engines, and was followed by Hibana, an arXiv paper on agentic inference for unified-memory devices.
editor-curated · source-linked
Arc
Oct 26Nov 10 · now
SCHEDULING · Oct 26Resin: a native scheduler for LLM inference engines1 source · show source ▾
LOCAL · Nov 7Hibana targets agentic inference on unified-memory devices1 source · show source ▾
Hibana: Fast Agentic Inference on Unified-Memory Devices
Moves the thread from servers to local devices, with a research take on agent workloads.
NOW · Nov 10Warmctl tackles vLLM cold starts1 source · show source ▾
Show HN: Warmctl – Fast cold starts for vLLM inference
Adds cold-start latency as a separate bottleneck, specific to vLLM deployments.
Day 1 Monday, Oct 26, 2026
Show HN: Resin, fast native scheduler for LLM inference engines
Opens the thread with a scheduling-layer approach to faster serving.
Day 2 Saturday, Nov 7, 2026
Hibana: Fast Agentic Inference on Unified-Memory Devices
Moves the thread from servers to local devices, with a research take on agent workloads.
Day 3 Tuesday, Nov 10, 2026
Show HN: Warmctl – Fast cold starts for vLLM inference
Adds cold-start latency as a separate bottleneck, specific to vLLM deployments.
What to watch — open questions
- Does Warmctl publish cold-start timings against a stock vLLM startup on named models and GPUs?
- Does Resin integrate with vLLM or SGLang, or does it require its own engine?
- Does Hibana release code, and which unified-memory hardware does it benchmark on?
How this thread was built
editor wrote the arc · 3 beats
Storylines are threaded mechanically from the feed: stories that share a distinctive anchor across multiple days and sources. Each item links to its original source. The evidence trace, current state, and open questions are written by the editor routine and refreshed whenever a new beat lands.