Commits

Branch selector

main

User selector

All users

All time

Commit history

Commits on Apr 7, 2025

• [merger] fix: move megatron import into megatron related branch (#958)

  Show description for 8400beb
  0x404

  authored
  8400bebView commit details

  Copy full SHA for 8400beb

  Browse repository at this point

• [distributed] enhancement: Make `register_center` named actor waiting time configurable & providing better error info (#947)

  Show description for c87e9f6
  

  hongpeng-guo

  and

  Copilot

  authored
  c87e9f6View commit details

  Copy full SHA for c87e9f6

  Browse repository at this point

• fix: support non-DTensor when converting fsdp checkpoints to hf model (#925)

  Show description for f20f552
  Altair-Alpha

  authored
  f20f552View commit details

  Copy full SHA for f20f552

  Browse repository at this point

• [megatron] feat: add gradient checkpointing in megatron backend (#944)

  Show description for d13434f
  ccclyu

  authored
  d13434fView commit details

  Copy full SHA for d13434f

  Browse repository at this point

• feat: Batch Rewards (#871)

  mertunsall

  authored
  82cbc43View commit details

  Copy full SHA for 82cbc43

  Browse repository at this point

Commits on Apr 6, 2025

• [sglang] feat: enhence sglang_rollout to handle image input (#824)

  Show description for 6efa018
  

  3 peopleauthored
  6efa018View commit details

  Copy full SHA for 6efa018

  Browse repository at this point

• [vllm] feat: enable FSDP and vLLM 0.8.2 to support DPSK v3 training. (#923)

  Show description for f8d1973
  BearBiscuit05

  authored
  f8d1973View commit details

  Copy full SHA for f8d1973

  Browse repository at this point

• [log] fix: validation metrics of reward and maj voting (#927)

  Show description for d2c6064
  tongyx361

  authored
  d2c6064View commit details

  Copy full SHA for d2c6064

  Browse repository at this point

• [sglang] ci: upgrade to sglang 0.4.4.post4 (#941)

  ocss884

  authored
  7753d37View commit details

  Copy full SHA for 7753d37

  Browse repository at this point

• [rf++] style: eos_mask to response_mask for reinforce++-baseline method (#938)

  Show description for 7afa6c6
  none0663

  authored
  7afa6c6View commit details

  Copy full SHA for 7afa6c6

  Browse repository at this point

• [ci] chore: reduce CI load part-2 (#942)

  eric-haibin-lin

  authored
  40c00c5View commit details

  Copy full SHA for 40c00c5

  Browse repository at this point

• [ci] chore: reduce CI load (#934)

  eric-haibin-lin

  authored
  526c090View commit details

  Copy full SHA for 526c090

  Browse repository at this point

• prompt: Fix computer_score in fsdp_workers.py (#629)

  Show description for 15263cb
  

  Django-Jiang

  and

  eric-haibin-lin

  authored
  15263cbView commit details

  Copy full SHA for 15263cb

  Browse repository at this point

• docs: add triton compile err to faq (#809)

  eric-haibin-lin

  authored
  7471e01View commit details

  Copy full SHA for 7471e01

  Browse repository at this point

• fix: seq-mean-token-sum loss (#931)

  tongyx361

  authored
  4d722b1View commit details

  Copy full SHA for 4d722b1

  Browse repository at this point

• [sglang] feat: SGLang rollout multinode support (#915)

  Show description for 7fc8330
  

  3 peopleauthored
  7fc8330View commit details

  Copy full SHA for 7fc8330

  Browse repository at this point

• [vllm] fix: skip vllm initialization with weight loading (#922)

  Show description for de46048
  BearBiscuit05

  authored
  de46048View commit details

  Copy full SHA for de46048

  Browse repository at this point

Commits on Apr 5, 2025

• docker: add verl-sglang dockerfile (#930)

  Show description for cc6dd90
  ocss884

  authored
  cc6dd90View commit details

  Copy full SHA for cc6dd90

  Browse repository at this point

• [math-verify] fix: TimeoutException (#929)

  tongyx361

  authored
  8447937View commit details

  Copy full SHA for 8447937

  Browse repository at this point

• Feat: support REINFORCE++-baseline and add script for REINFORCE++ (#908)

  Show description for 30259d2
  hijkzzz

  authored
  30259d2View commit details

  Copy full SHA for 30259d2

  Browse repository at this point

Commits on Apr 4, 2025

• feat: Add multi-turn SFT support (#195)

  xingyaoww

  authored
  fb03941View commit details

  Copy full SHA for fb03941

  Browse repository at this point

• tool: add diagnosis script (#918)

  Show description for 4f245a3
  eric-haibin-lin

  authored
  4f245a3View commit details

  Copy full SHA for 4f245a3

  Browse repository at this point

• docs: update installation and adoption docs (#921)

  eric-haibin-lin

  authored
  0fc8e77View commit details

  Copy full SHA for 0fc8e77

  Browse repository at this point

• [dataset] refactor: remove unused filter_prompts parameter from RLHFDataset (#889)

  Show description for 0407cad
  0x404

  authored
  0407cadView commit details

  Copy full SHA for 0407cad

  Browse repository at this point

• fix: set gen_batch_size based on config (#909)

  tongyx361

  authored
  d5a1c81View commit details

  Copy full SHA for d5a1c81

  Browse repository at this point

• [dataset] refactor: use hf Dataset instead of pandas DataFrame in RLHFDataset for speedup (#890)

  Show description for 6974bba
  

  0x404

  and

  hiyouga

  authored
  6974bbaView commit details

  Copy full SHA for 6974bba

  Browse repository at this point

• [log] fix: log after generate_sequences (#819)

  tongyx361

  authored
  6d931dfView commit details

  Copy full SHA for 6d931df

  Browse repository at this point

• [algo] misc: remove redundant tile([1, response_length]), efficient broadcast instead (#868)

  Show description for f9256b8
  dirtyDan0

  authored
  f9256b8View commit details

  Copy full SHA for f9256b8

  Browse repository at this point

Commits on Apr 3, 2025

• [recipe] feat: integrate DAPO and provide reproduction script (#623)

  Show description for 3a27a98
  

  tongyx361

  and

  PeterSH6

  authored
  3a27a98View commit details

  Copy full SHA for 3a27a98

  Browse repository at this point

• [dev] feat: default VSCode repo settings to help consistency with CI (#894)

  Show description for cc612db
  tongyx361

  authored
  cc612dbView commit details

  Copy full SHA for cc612db

  Browse repository at this point

• test: update vllm_spmd test for > 0.7.3 (#861)

  Show description for 1a7e53d
  BearBiscuit05

  authored
  1a7e53dView commit details

  Copy full SHA for 1a7e53d

  Browse repository at this point

• reuse GPTModel, try to fix CI issue (#884)

  Show description for 0338805
  ETOgaosion

  authored
  0338805View commit details

  Copy full SHA for 0338805

  Browse repository at this point

• fix: the error is not raised when using both megatron and hf inference (#885)

  Show description for b6dc157
  wkcn

  authored
  b6dc157View commit details

  Copy full SHA for b6dc157

  Browse repository at this point

• docs: add config docs for evaluation.yaml (#886)

  Show description for b0e0ac5
  yyDing1

  authored
  b0e0ac5View commit details

  Copy full SHA for b0e0ac5

  Browse repository at this point

• fix: misleading eos_mask->response_mask (#878)

  Show description for 8cae42d
  dirtyDan0

  authored
  8cae42dView commit details

  Copy full SHA for 8cae42d

  Browse repository at this point