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, 12:15 UTC
[CI][Bugfix] Fix failing V1 Test due to missing 'cache_salt' arg (#17500)
Signed-off-by: mgoin <mgoin64@gmail.com>
Michael Goin committed
Apr 30, 2025 at 22:03 UTC
aa4502e7f3d9f53f093bb9b91607617a2223156b
1 file changed
+1
tests/v1/engine/test_engine_core_client.py
+1
@@ -306,6 +306,7 @@ def test_kv_cache_events(
306
eos_token_id=None,
307
arrival_time=time.time(),
308
lora_request=None,
309
+ cache_salt=None,
310
)
311
client.add_request(request)
312