All pull requests

Pull requests

• Add opt-in policies for unbridged Harbor skycap rollouts

  #2514·jadenfix opened Oct 19, 2026Contributor·

  ·
  1

• [megatron][vllm] Qwen3.8-Flash-Next (qwen4_exp) support: Megatron bridge, QSA sparse attention, GSM8K + DAPO recipes

  #2513·xinyuangui2 opened Oct 17, 2026Collaborator·6 of 10 tasks·

  ·

• [SkyCap] Support OpenAI Responses API

  #2510·kyuds opened Oct 17, 2026Collaborator·

  ·
  1

• [megatron][vlm] freeze_language_model / freeze_vision_model / freeze_vision_projection

  #2509·gc-anyscale opened Oct 16, 2026Contributor·

  ·
  8

• [megatron] Initialize a LoRA policy from a PEFT adapter (lora.init_adapter_path)

  #2508·avigyabb opened Oct 16, 2026Collaborator·

  ·

• [fsdp] Initialize a LoRA policy from a PEFT adapter (lora.init_adapter_path)

  #2507·avigyabb opened Oct 16, 2026Collaborator·

  ·

• [LoRA] Add the PEFT adapter import library (parsing, scales, fused stacking)

  #2506·avigyabb opened Oct 16, 2026Collaborator·

  ·

• [megatron] Let a LoRA-wrapped output_layer answer for its base linear

  #2505·avigyabb opened Oct 16, 2026Collaborator·

  ·
  8

• [tinker] Free the colocate placement group after a failed model build

  #2504·spicysharkco opened Oct 16, 2026·

  ·
  1

  1

• [LoRA] Initialize LoRA policies from a PEFT adapter (lora.init_adapter_path): resume Tinker runs on Megatron/FSDP

  #2503·avigyabb opened Oct 16, 2026Collaborator·

  ·
  3

• [inference] /skyrl/v1/generate: accept multimodal features

  #2501·xinyuangui2 opened Oct 15, 2026Collaborator·

  ·
  11

• [sft] Add lazy_vlm_dataset: tokenize VLM datasets per fetch instead of holding every row's pixel_values

  #2498·gc-anyscale opened Oct 15, 2026Contributor·

  ·
  7

  

• [skycap][bugfix] Preserve extracted arguments without promoting failed parses

  x-lila
  #2497·cbanbury-lila opened Oct 15, 2026Contributor·

  ·
  6

  

• [docs][skycap] Add a skycap page to the SkyRL docs

  #2494·kouroshHakha opened Oct 15, 2026Collaborator·

  ·

• WIP: [Feature] Add ADAPO controller

  #2491·catherinelee274 opened Oct 15, 2026·

  ·
  7

• [feat][megatron] Support optimizer state offload to disk (optimizer_offload_to_disk)

  #2490·SumanthRH opened Oct 15, 2026Member·

  ·
  1

• [examples][skycap] Carry the sampler's support logprobs through harbor_skycap

  x-lila
  #2485·dyurk-lila opened Oct 14, 2026Collaborator·3/3·

  ·
  4

  

• [skyrl-train] Score centering over the recorded sample support

  run_gpu_cirun_megatron_gpu_cix-lila
  #2484·dyurk-lila opened Oct 14, 2026Collaborator·2/3·

  ·
  6

• [skyrl-train] Carry sample support as CSR from capture through replay

  run_gpu_cirun_megatron_gpu_cix-lila
  #2483·dyurk-lila opened Oct 14, 2026Collaborator·1/3·

  ·
  11

  

• [chore] Use random tokens in the full context trainer's dummy batch

  #2479·SumanthRH opened Oct 14, 2026Member·

  ·

• [harbor] Run Harbor's modal environment on Ray Sandbox

  #2478·xyuzh opened Oct 13, 2026·

  ·
  10

• [feat][megatron] Add an opt-in streaming write for async checkpoints

  #2477·bvolpato opened Oct 13, 2026Contributor·

  ·

• [feat][train] Honor return_per_token_outputs in the RL loss

  #2476·bvolpato opened Oct 13, 2026Contributor·

  ·

• [feat][train] Run fully async checkpoint and HF export during eval

  #2475·bvolpato opened Oct 13, 2026Contributor·

  ·

• fix(examples): align custom policy loss with trainer contract

  #2474·raghulchandramouli opened Oct 13, 2026·

  ·
  2