What's Changed
- Fix GRPO + vLLM colocate + PEFT hang on non-NVLink hardware by @albertvillanova in #6139
- Fix dataset fingerprinting in DPO/SFT tokenization by @qgallouedec in #6206
- Pass GPU device_ids to barrier fix in GRPO + vLLM colocate + PEFT by @albertvillanova in #6187
- Integrate the new response parsing API by @qgallouedec in #5791
- Fix
add_response_schematests for the newparse_responseprefix requirement by @qgallouedec in #6236 - Add prompt-learning guard for PEFT with Liger in GRPO by @albertvillanova in #6186
- Fix activation offload storage dedupe reuse by @winglian in #6241
Full Changelog: v1.7.0...v1.7.1