[serving] Fix continuous batching JSON response serialization#45057
Merged
NathanHB merged 10 commits intohuggingface:mainfrom Mar 31, 2026
Merged
[serving] Fix continuous batching JSON response serialization#45057NathanHB merged 10 commits intohuggingface:mainfrom
NathanHB merged 10 commits intohuggingface:mainfrom
Conversation
Change model_dump_json() to model_dump() to avoid double JSON encoding. When using continuous batching with stream=false, the response was being double-encoded as a string instead of returning a proper JSON object.
LysandreJik
reviewed
Mar 27, 2026
Member
LysandreJik
left a comment
LysandreJik
left a comment
There was a problem hiding this comment.
Thank you! Can you add a test so that this gets caught?
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
Test verifies that non-streaming responses with continuous batching return proper JSON objects rather than double-encoded JSON strings. This is a regression test for the fix where model_dump_json() was changed to model_dump() in the continuous batching response handler.
Member
Author
|
@bot /style |
Changed dependency from personal fork to official huggingface/transformers@main for production use of the evaluation script.
ArthurZucker
approved these changes
Mar 30, 2026
Collaborator
ArthurZucker
left a comment
ArthurZucker
left a comment
There was a problem hiding this comment.
Nice!!! fyi @remi-or
NathanHB
force-pushed
the
fix-continuous-batching-json-response
branch
from
ec55108 to
5fddeb2
Compare
Contributor
|
[For maintainers] Suggested jobs to run (before merge) run-slow: clap, deit, depth_anything, dpt, ijepa, llama4, marian, mimi |
- Add --cb-block-size, --cb-num-blocks, --cb-max-batch-tokens, --cb-max-memory-percent, and --cb-use-cuda-graph flags - Flags allow users to customize KV cache and performance settings for continuous batching - Update transformers_serve_cb_eval_job.py to support and pass through CB config arguments - Update transformers dependency to use NathanHB/transformers@fix-continuous-batching-json-response branch - All arguments use auto-inference defaults when not specified (backward compatible)
sirzechs66
pushed a commit
to sirzechs66/transformers
that referenced
this pull request
Mar 31, 2026
…gface#45057) * Fix continuous batching JSON response serialization Change model_dump_json() to model_dump() to avoid double JSON encoding. When using continuous batching with stream=false, the response was being double-encoded as a string instead of returning a proper JSON object. * add example script eval-job * fix script * Add test for continuous batching non-streaming JSON response Test verifies that non-streaming responses with continuous batching return proper JSON objects rather than double-encoded JSON strings. This is a regression test for the fix where model_dump_json() was changed to model_dump() in the continuous batching response handler. * fix ci * Update eval script to use official transformers repo main branch Changed dependency from personal fork to official huggingface/transformers@main for production use of the evaluation script. * add kernels and flash attn 2 * Add continuous batching configuration CLI arguments to serve command - Add --cb-block-size, --cb-num-blocks, --cb-max-batch-tokens, --cb-max-memory-percent, and --cb-use-cuda-graph flags - Flags allow users to customize KV cache and performance settings for continuous batching - Update transformers_serve_cb_eval_job.py to support and pass through CB config arguments - Update transformers dependency to use NathanHB/transformers@fix-continuous-batching-json-response branch - All arguments use auto-inference defaults when not specified (backward compatible) * Add thread lock for manager creation to avoid double manager * change transformers dep --------- Co-authored-by: remi-or <remi.pierre_o@orange.fr>
SangbumChoi
pushed a commit
to SangbumChoi/transformers
that referenced
this pull request
Apr 4, 2026
…gface#45057) * Fix continuous batching JSON response serialization Change model_dump_json() to model_dump() to avoid double JSON encoding. When using continuous batching with stream=false, the response was being double-encoded as a string instead of returning a proper JSON object. * add example script eval-job * fix script * Add test for continuous batching non-streaming JSON response Test verifies that non-streaming responses with continuous batching return proper JSON objects rather than double-encoded JSON strings. This is a regression test for the fix where model_dump_json() was changed to model_dump() in the continuous batching response handler. * fix ci * Update eval script to use official transformers repo main branch Changed dependency from personal fork to official huggingface/transformers@main for production use of the evaluation script. * add kernels and flash attn 2 * Add continuous batching configuration CLI arguments to serve command - Add --cb-block-size, --cb-num-blocks, --cb-max-batch-tokens, --cb-max-memory-percent, and --cb-use-cuda-graph flags - Flags allow users to customize KV cache and performance settings for continuous batching - Update transformers_serve_cb_eval_job.py to support and pass through CB config arguments - Update transformers dependency to use NathanHB/transformers@fix-continuous-batching-json-response branch - All arguments use auto-inference defaults when not specified (backward compatible) * Add thread lock for manager creation to avoid double manager * change transformers dep --------- Co-authored-by: remi-or <remi.pierre_o@orange.fr>
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
5 participants
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.
Change model_dump_json() to model_dump() to avoid double JSON encoding. When using continuous batching with stream=false, the response was being double-encoded as a string instead of returning a proper JSON object.
Added a UV script to run GPQA using transformer-serve:
69c695adf900226fc14ae1abAttributeError: 'NoneType' object has no attribute 'generated_tokens'- Server starts but all requests fail69c696bcbf20ec90acee2ffa