Issues

• [RFC]: Native Rust/CUDA inference for Mapika/decider-2b

  RFC
  ThinkFlowLab/system1-omni#57 · Filter by author hsliuustc0106 opened on Oct 1, 2026

• [New Model]: Native Rust/CUDA support for Open-Jev-27B-v1.1

  new model
  ThinkFlowLab/system1-omni#54 · Filter by author hsliuustc0106 opened on Sep 30, 2026

• [Feature]: Community help wanted — CPU-only API tests in CI

  enhancementhelp wanted
  ThinkFlowLab/system1-omni#46 · Filter by author hsliuustc0106 opened on Sep 30, 2026
  1

  

• [Doc]: Community help wanted — documentation site and GitHub Pages

  documentationhelp wanted
  ThinkFlowLab/system1-omni#45 · Filter by author hsliuustc0106 opened on Sep 30, 2026
  4

• [Performance]: Reproducible Laya benchmarks against the original runtime

  help wantedperformance
  ThinkFlowLab/system1-omni#39 · Filter by author hsliuustc0106 opened on Sep 29, 2026

• Cua-S1 multimodal stack: validation results and cross-PR integration checklist

  ThinkFlowLab/system1-omni#36 · Filter by author Levius-Fubuki opened on Sep 29, 2026
  2

• [New Model]: LFM2.5-350M choice execution

  ThinkFlowLab/system1-omni#31 · Filter by author prettygirlisnotme opened on Sep 28, 2026

• [New Model]: Support Kev (0.5B–9B) — second Qwen3.5 decision model, reusing the qwen3_5 CUDA backend

  ThinkFlowLab/system1-omni#27 · Filter by author xiaoyu-xyz opened on Sep 28, 2026

• [RFC]: Native Laya inference with Rust and CUDA

  ThinkFlowLab/system1-omni#14 · Filter by author linear3735 opened on Sep 28, 2026
  1

• [New Model]: Support Cua-S1 4B 0.2 — community help wanted

  help wantednew model
  ThinkFlowLab/system1-omni#10 · Filter by author hsliuustc0106 opened on Sep 27, 2026
  8

  

• [RFC] Support emerging System 1 models, with CLM as the second model after LAYA

  ThinkFlowLab/system1-omni#9 · Filter by author Yunaik opened on Sep 27, 2026
  2

• [Help wanted] Accelerated Laya serving on Apple Silicon

  ThinkFlowLab/system1-omni#3 · Filter by author hsliuustc0106 opened on Sep 26, 2026
  4