Skip to content

feat(client): pass through vLLM weight_versions spans #195

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
faresobeid merged 1 commit into from
Oct 19, 2026
Merged

feat(client): pass through vLLM weight_versions spans #195

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 6 additions & 3 deletions renderers/client.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -261,9 +261,11 @@ async def generate(
Returns a dict with: request_id, prompt_ids, renderer_prompt_ids,
mm_placeholders, completion_ids, completion_logprobs, content,
reasoning_content, tool_calls, finish_reason, routed_experts,
multi_modal_data, prompt_attribution. ``renderer_prompt_ids`` is the
unexpanded logical prompt when ``process_multimodal=False`` and ``None``
otherwise.
weight_versions, multi_modal_data, prompt_attribution.
``renderer_prompt_ids`` is the unexpanded logical prompt when
``process_multimodal=False`` and ``None`` otherwise. ``weight_versions``
is vLLM's (>= 0.32) list of ``{version, start, end}`` spans over
completion-token indexes, or ``None`` when the engine labels none.

``prompt_attribution`` is the renderer's :class:`RenderedTokens` for
the prompt — either the one this call computed via
Expand Down Expand Up @@ -431,6 +433,7 @@ def _prepare():
"reasoning_complete": parsed.reasoning_complete,
"routed_experts": routed_experts,
"sampling_mask": sampling_mask,
"weight_versions": choice.get("weight_versions"),
# The mm sidecar consumed on the request side, surfaced back so
# callers can persist it on the trajectory step for downstream
# multi-turn bridging and training-sample construction.
Expand Down
Loading