All pull requests

Pull requests

• docs: add a supported models and hardware page

  #60·twu3202 opened Oct 1, 2026Contributor·

  ·

• cua_s1: load and validate native vision checkpoints on CPU

  #59·Levius-Fubuki opened Oct 1, 2026Collaborator·

  ·

• test: expand frontend API integration coverage

  #58·MrDongsls opened Oct 1, 2026·

  ·
  1

• cua_s1: accept image embeddings and 3D positions in native language model

  #56·Levius-Fubuki opened Oct 1, 2026Collaborator·

  ·
  3

• open_jev: add native Rust/CUDA text worker

  #55·hsliuustc0106 opened Sep 30, 2026Contributor·

  ·
  1

• Add Cua-S1 multimodal reference tensor exports

  #53·Levius-Fubuki opened Sep 30, 2026Collaborator·

  ·
  2

• Run Laya encoder and decision layers on CUDA

  #49·linear3735 opened Sep 30, 2026·

  ·

• Keep Laya weights and workspace on CUDA

  #48·linear3735 opened Sep 30, 2026·

  ·

• Add CUDA resource ownership

  #47·linear3735 opened Sep 30, 2026·

  ·

• Decode Laya answers on CPU

  #44·linear3735 opened Sep 30, 2026·

  ·

• Add Laya request preprocessing

  #43·linear3735 opened Sep 30, 2026·

  ·

• Bound health checks and buffered worker responses

  #42·linear3735 opened Sep 30, 2026·

  ·

• Add automatic Graph selection with shared Cua-S1 worker budgets

  #38·Levius-Fubuki opened Sep 29, 2026Collaborator·

  ·
  1

• Add instance-local rule buckets to the Cua-S1 multimodal worker

  #37·Levius-Fubuki opened Sep 29, 2026Collaborator·

  ·
  1

• feat(frontend): own the engine in a worker thread with a bounded queue

  #35·xiaoyu-xyz opened Sep 29, 2026·

  ·
  1

• feat(frontend): add the in-process engine contract and HTTP service

  #34·xiaoyu-xyz opened Sep 29, 2026·

  ·

• Bound Cua-S1 Graph capture work with request admission and cooldown

  #33·Levius-Fubuki opened Sep 29, 2026Collaborator·

  ·
  2

• Add LFM2.5-350M choice worker with candidate batching

  #32·prettygirlisnotme opened Sep 28, 2026·

  ·

• Laya on Apple Silicon: worker, benchmarks and recipe

  #30·cacheline999 opened Sep 28, 2026·

  ·
  1

  6

• [CLM 2/2] Reach the encoder, answer requests, and check against CLM

  #29·xiaoyu-xyz opened Sep 28, 2026·

  ·
  1

• [CLM 1/2] Checkpoint and typed decision scoring

  #28·xiaoyu-xyz opened Sep 28, 2026·

  ·
  1

• cuda: add the backend contract and its checker

  #25·xiaoyu-xyz opened Sep 28, 2026·

  ·
  1

• [Recipe] Run CLM behind the frontend, and compare engine responses

  #23·xiaoyu-xyz opened Sep 28, 2026·

  ·
  1

• Serve Cua-S1 multimodal requests with bounded segmented CUDA Graphs

  #22·by Levius-Fubuki was merged Oct 1, 2026Collaborator·

  ·
  2

• Add CPU checkpoint loading for Laya

  #21·linear3735 opened Sep 28, 2026·

  ·
  3