A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 03:30 UTC
[Doc] Syntax highlight request responses as JSON instead of bash (#20582)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Harry Mellor committed
Jul 8, 2025 at 04:02 UTC
6e428cdd7a5d986f954452fb337821942afb0844
1 file changed
+6
-6
docs/serving/openai_compatible_server.md
+6
-6
@@ -448,7 +448,7 @@ curl -v "http://127.0.0.1:8000/classify" \
448
449
??? console "Response"
450
451
- ```bash
451
+ ```json
452
{
453
"id": "classify-7c87cac407b749a6935d8c7ce2a8fba2",
454
"object": "list",
@@ -496,7 +496,7 @@ curl -v "http://127.0.0.1:8000/classify" \
496
497
??? console "Response"
498
499
- ```bash
499
+ ```json
500
{
501
"id": "classify-9bf17f2847b046c7b2d5495f4b4f9682",
502
"object": "list",
@@ -566,7 +566,7 @@ curl -X 'POST' \
566
567
??? console "Response"
568
569
- ```bash
569
+ ```json
570
{
571
"id": "score-request-id",
572
"object": "list",
@@ -608,7 +608,7 @@ The total number of pairs is `len(text_2)`.
608
609
??? console "Response"
610
611
- ```bash
611
+ ```json
612
{
613
"id": "score-request-id",
614
"object": "list",
@@ -657,7 +657,7 @@ The total number of pairs is `len(text_2)`.
657
658
??? console "Response"
659
660
- ```bash
660
+ ```json
661
{
662
"id": "score-request-id",
663
"object": "list",
@@ -736,7 +736,7 @@ Result documents will be sorted by relevance, and the `index` property can be us
736
737
??? console "Response"
738
739
- ```bash
739
+ ```json
740
{
741
"id": "rerank-fae51b2b664d4ed38f5969b612edff77",
742
"model": "BAAI/bge-reranker-base",