v0.7.0

What's Changed

• Added verified answers to the logging by @abaheti95 in #63
• Adding GPU CI back by @dakinggg in #64
• Fix args propagation by @dakinggg in #65
• Fix weight propagation by @bcui-db in #66
• Microbatching fixes by @dakinggg in #71
• Make myself admin by @gupta-abhay in #72
• Update ci-testing to latest version by @dakinggg in #70
• Move generate to be done via prompt_token_ids by @bcui-db in #73
• Add GRPO assert that we need more than one generation by @bcui-db in #74
• Adding a Math format verifier by @gupta-abhay in #75
• Ping foundry version and hash to prepare foundry upgrade by @bowenyang008 in #76
• Bump to torch 2.7 by @bowenyang008 in #77
• Allow DPO reference model to be loaded from LoadCheckpoint callback by @dakinggg in #80
• Set default value as this is only used for local debugging by @gupta-abhay in #84
• Add More Codeowners by @bcui-db in #86
• Fix reward timeouts by @dakinggg in #87
• Remove llama models as defaults by @gupta-abhay in #88
• Skip initial vLLM weight load. by @dakinggg in #89
• Fix memory leak by @dakinggg in #90
• Renaming and Organization of RL algorithms in preparation for Development by @jdchang1 in #83
• Causal classifier by @alextrott16 in #8
• Vllm import Hotfix by @jdchang1 in #91
• Fixing entropy calculation by @abaheti95 in #85

Full Changelog: v0.5.0...v0.7.0