Stream the same text the non-streaming response returns

[santhnm2]

• I, the PR author, have personally reviewed every line of this PR.

What does this PR do?

The streaming chat path decoded with DecodeStream(skip_special_tokens=True), which drops every added token flagged special. The non-streaming path drops only the tokenizer's special-tokens map (all_special_tokens) and trailing EOS ids. Chat tokenizers commonly flag their reasoning and tool-call markers as special without putting them in that map (e.g. <think>, </think>, <tool_call>, </tool_call>), so in a stream the reasoning parser never saw </think>: the answer and the tool-call markup ended up in reasoning_content and no tool call was parsed. Thinking-disabled streams and every non-streaming reply were unaffected.

Decode with skip_special_tokens=False and drop exactly the ids the non-streaming path drops: all_special_ids and the model EOS ids (model_eos_token_ids), from both the generated tokens and the prompt prefill. Tokens in the special-tokens map (BOS/EOS/pad) are still dropped.

⚠️ For major changes (either in lines of code or in its impact), please make sure to first share a design doc with the team. If you're unsure what's the best way to do so, contact @NVIDIA/mcore-oncall.

Issue tracking

For PRs from open-source community contributors:

• New features: a linked issue is required. Please open a feature request and reference it here before submitting the PR.
• Small updates (bug fixes, minor improvements): a linked issue is recommended and will accelerate the PR review process.

Linked issue:

Contribution process

Pre-checks

• I have added relevant unit tests
• I have added relevant functional tests
• If this PR adds or changes a GPU kernel (Triton, jit_fuser/torch.compile, CUDA extension, TE or external-library dispatch, or a scatter/index accumulation), I have added or updated its bit-exact determinism test and registered it in tests/unit_tests/determinism/kernels/manifest.py (guide)
• I have added proper typing to my code Typing guidelines
• I have added relevant documentation
• I have run the autoformatter.sh on my PR

Code review

Feel free to message or comment @NVIDIA/mcore-oncall to help accelerate your merge into main. The less complex your PR is, the faster it will be approved and merged!

All PRs start as draft. If you open a non-draft PR, it will be automatically converted to draft.

Step 1: Mark PR as "Ready for Review"

1. When your PR is ready, click Ready for Review.
2. An oncall reviewer is auto-assigned and expert reviewers are notified based on your changes.
   • Some PRs may jump straight to step 2. This is determined by .github/CODEOWNERS.

⚠️ Only mark as ready once merge-conflicts are resolved and the CI is passing.
Final Review might get declined if these requirements are not fulfilled.

Step 2: Final Review

For PRs that change megatron/core, once all expert reviewers have approved, the Final Review label is applied automatically and final reviewers are assigned.

For PRs outside megatron/core, this step is skipped.

Step 3: Approved

Once all required reviewers have approved, the Approved label is applied automatically.

Merge

Any member of mcore-engineers will be able to merge your PR.

[copy-pr-bot]

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.