[Feature] The 45VL supports prompt_token_ids + messages input. - #5148
Merged
Merged
Conversation
|
Thanks for your contribution! |
Codecov Report❌ Patch coverage is Additional details and impacted files@@ Coverage Diff @@
## develop #5148 +/- ##
==========================================
Coverage ? 59.91%
==========================================
Files ? 317
Lines ? 38789
Branches ? 5841
==========================================
Hits ? 23242
Misses ? 13709
Partials ? 1838
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
LiqinruiG
reviewed
Nov 24, 2025
| prompt_token_ids = request.get("prompt_token_ids", []) | ||
| prompt_token_ids_len = len(prompt_token_ids) | ||
| if not request.get("messages"): | ||
| outputs["input_ids"].append(prompt_token_ids) |
| messages = request.get("messages") | ||
| if messages: | ||
| self._check_mm_limits(messages) | ||
| request.setdefault("enable_thinking", True) |
Collaborator
There was a problem hiding this comment.
这里应该不能简单的赋值。 需要看 prompt_token_ids 情况。 这里等 #4302 的 PR 合入之后再调整吧。
chang-wenbin
pushed a commit
to chang-wenbin/FastDeploy
that referenced
this pull request
Mar 2, 2026
…ePaddle#5148) * support prompt_token_ids + messages * fix bug * refact code structure * support cache mm items * refact code structure * delete test cases * modify unit test * add unit test * add unit test * fix append * add check for messages
xiaoguoguo626807
pushed a commit
to xiaoguoguo626807/FastDeploy
that referenced
this pull request
May 7, 2026
…ePaddle#5148) * support prompt_token_ids + messages * fix bug * refact code structure * support cache mm items * refact code structure * delete test cases * modify unit test * add unit test * add unit test * fix append * add check for messages
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Motivation
When triggering multiple rounds with RLC, we aim to use the prompt_ids and completion_ids from the previous round as input for the current round without requiring concatenation. Additionally, we wish to pass image information via the message field.
Modifications
The
process_request_dictfunction inernie4_5_vl_processornow supports reading theprompt_token_idsfield from the request as input. It also supports reading multimodal information from themessagesfield in this scenario.Usage or Command
No change in manual command
Accuracy Tests
No need
Checklist
[FDConfig],[APIServer],[Engine],[Scheduler],[PD Disaggregation],[Executor],[Graph Optimization],[Speculative Decoding],[RL],[Models],[Quantization],[Loader],[OP],[KVCache],[DataProcessor],[BugFix],[Docs],[CI],[Optimization],[Feature],[Benchmark],[Others],[XPU],[HPU],[GCU],[DCU],[Iluvatar],[Metax]]pre-commitbefore commit.releasebranch, make sure the PR has been submitted to thedevelopbranch, then cherry-pick it to thereleasebranch with the[Cherry-Pick]PR tag.