build: update trl requirement from <=0.21.0 to <=1.3.0

[dependabot]

Updates the requirements on trl to permit the latest version.

Release notes

Sourced from trl's releases.

v1.3.0

Features

Qwen 3.6 integration

TRL v1.3 ships training support for the new Qwen 3.6 family (Qwen/Qwen3.6-27B, Qwen/Qwen3.6-35B-A3B). Qwen 3.6 reuses the Qwen3_5Moe* architecture but ships a slightly different chat template (adds a preserve_thinking flag, tweaks tool-arg stringification), so exact-string template matching needed updates across the stack.

What landed:

• Chat templates: qwen3_6.jinja (verbatim from upstream) and qwen3_6_training.jinja (prefix-preserving + {% generation %} markers for assistant_only_loss=True)
• Response schema: routes to the existing qwen3_5_schema for tool-call parsing — output format unchanged
• Tiny test models for VLM training: tiny-Qwen3_5MoeForConditionalGeneration-3.6 (with MoE-specific shrinking)
• Test matrix updated across SFT/DPO/GRPO/RLOO test_(train|training)_vlm cases

from trl import SFTConfig, SFTTrainer
trainer = SFTTrainer(
model="Qwen/Qwen3.6-27B",
args=SFTConfig(assistant_only_loss=True),  # works out of the box
train_dataset=dataset,
)
trainer.train()

Tool-calling agent training also works end-to-end via the existing Qwen 3.5 response schema:

from trl import GRPOConfig, GRPOTrainer
def multiply(a: int, b: int) -> int:
"""
Multiplies two integers.
Args:
    a: The first integer.
    b: The second integer.
Returns:
The product of the two integers.
"""
return a * b

trainer = GRPOTrainer(
model="Qwen/Qwen3.6-27B",
reward_funcs=my_reward_fn,
args=GRPOConfig(...),
</tr></table>

... (truncated)

Commits

• 9679645 Release: v1.3 (#5647)
• 2f10689 Qwen3.6 integration (#5642)
• 3aa9519 Align KTO with DPO: Remove BOS/EOS handling (#5635)
• 43cbd78 Renaming of internal variables: async_reward_X to async_X (#5616)
• c693ca1 Fix entropy calculation in SFT (#5620)
• 208337c Hotfix CI: Add ruff dependency to doc-builder style check (#5634)
• 4c8b2e9 Align KTO with DPO: Move completion assembly from _prepare_dataset to data co...
• b43476a Align and update doc-builder commit hash in CI GitHub Actions (#5631)
• 1996c39 Add doc-builder style check to pre-commit and CI (#5630)
• a9cfe47 Use PreTrainedTokenizerBase for tokenizer type hints (#5629)
• Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)