[Frontend] Add stateless /v1/responses/render endpoint (#50195)

Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
This commit is contained in:
Francisco Javier Arceo
2026-09-07 12:50:42 +00:00
committed by GitHub
co-authored by OpenAI Codex
parent 5e6f6a8ed4
commit 6a2a2bb02b
19 changed files with 1228 additions and 298 deletions
+2
View File
@@ -141,6 +141,8 @@ For further details on renderer APIs, please refer to [this page](renderer.md).
- Render completion requests
- [Chat Completions Render API](renderer.md) (`/v1/chat/completions/render`)
- Render chat completions
- [Responses Render API](renderer.md) (`/v1/responses/render`)
- Render self-contained Responses requests
### Derenderer APIs
+23
View File
@@ -25,6 +25,29 @@ VLLM_ENABLE_SCALE_OUT_ENDPOINTS=1 vllm serve <model>
- Render completion requests
- [Chat Completions Render API](renderer.md) (`/v1/chat/completions/render`)
- Render chat completions
- [Responses Render API](renderer.md) (`/v1/responses/render`)
- Render a self-contained Responses request
The Responses render endpoint uses the same prompt construction as
`/v1/responses` and returns one token-in `GenerateRequest`. It is stateless:
inline history is supported, but `previous_response_id` is not. Callers must
resolve stored response state and include the resulting history in the request
before rendering.
For multimodal requests, the `GenerateRequest` contains the model-processed
multimodal payload, which can be substantially larger than the source image or
video. The caller must forward that payload unchanged to the generation service
and provision transport limits and memory accordingly.
```bash
curl http://localhost:8000/v1/responses/render \
-H "Content-Type: application/json" \
-d '{
"model": "meta-llama/Llama-3.1-8B-Instruct",
"input": "Explain prefix caching in one sentence.",
"max_output_tokens": 32
}'
```
For the post processing counterpart that turns generated token IDs back into OpenAI compatible responses, see the [Derenderer APIs](derenderer.md).