ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Fix older-TRL GRPO resume branch wiring

Browse source
This commit is contained in:
Daniel Han 2026-03-12 10:16:52 +00:00
commit c8c8dafc04
1 changed files with 1 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

4
unsloth/models/rl.py
View file

@ -1840,8 +1840,6 @@ def patch_functions(RLTrainer, trainer_file, RLTrainer_name, all_imports, import
new_vllm_part,
flags = re.DOTALL, # Ensure . matches newlines [[5]]
)
init = init.replace(vllm_part, new_vllm_part)
else:
new_vllm_part = (
f"\n{' '*8}if {args}.use_vllm:\n"
@ -1851,7 +1849,7 @@ def patch_functions(RLTrainer, trainer_file, RLTrainer_name, all_imports, import
f"{' '*12}self.accelerator.wait_for_everyone()\n"
f"\n{' '*8}else:\n"
)
init = init.replace(vllm_part, new_vllm_part)
init = init.replace(vllm_part, new_vllm_part)
# Search for vLLM calling in all child functions
functions = dir(RLTrainer)