Add /v1/chat/completions/batch endpoint for batched chat completions (#38011)

Signed-off-by: Matej Rojec <64556640+MatejRojec@users.noreply.github.com>
2026-03-26 05:13:33 +01:00
parent e6bf9f15ec
commit 2908094567
8 changed files with 771 additions and 21 deletions
--- a/tests/entrypoints/openai/test_openai_schema.py
+++ b/tests/entrypoints/openai/test_openai_schema.py
@@ -174,6 +174,7 @@ def test_openapi_stateless(case: Case):
    timeout = {
        # requires a longer timeout
        ("POST", "/v1/chat/completions"): LONG_TIMEOUT_SECONDS,
+        ("POST", "/v1/chat/completions/batch"): LONG_TIMEOUT_SECONDS,
        ("POST", "/v1/completions"): LONG_TIMEOUT_SECONDS,
        ("POST", "/v1/messages"): LONG_TIMEOUT_SECONDS,
    }.get(key, DEFAULT_TIMEOUT_SECONDS)