Support embedding models in V1 (#16188)

Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Signed-off-by: Max de Bayser <maxdebayser@gmail.com>
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
Co-authored-by: 22quinn <33176974+22quinn@users.noreply.github.com>
This commit is contained in:
Maximilien de Bayser
2025-06-18 21:36:33 -07:00
committed by GitHub
co-authored by 22quinn
parent 4959915089
commit 799397ee4f
56 changed files with 889 additions and 281 deletions
+3
View File
@@ -145,6 +145,7 @@ def run_with_both_engines(request, monkeypatch):
# Automatically runs tests twice, once with V1 and once without
use_v1 = request.param
# Tests decorated with `@skip_v1` are only run without v1
skip_v0 = request.node.get_closest_marker("skip_v0")
skip_v1 = request.node.get_closest_marker("skip_v1")
if use_v1:
@@ -152,6 +153,8 @@ def run_with_both_engines(request, monkeypatch):
pytest.skip("Skipping test on vllm V1")
monkeypatch.setenv('VLLM_USE_V1', '1')
else:
if skip_v0:
pytest.skip("Skipping test on vllm V0")
monkeypatch.setenv('VLLM_USE_V1', '0')
yield