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 8, 05:00 UTC
[BugFix] Fix sp tests (#34716)
Signed-off-by: Richard Zou <zou3519@gmail.com>
Richard Zou committed
Feb 17, 2026 at 12:07 UTC
7967e854da4868872b4b13d2b7f039061fee50fe
1 file changed
+1
-1
tests/compile/correctness_e2e/test_sequence_parallel.py
+1
-1
@@ -229,7 +229,7 @@ def _compare_sp(
229
if chunked_prefill:
230
common_args.append("--enable-chunked-prefill")
231
if eager_mode:
232
- common_args.append("--enforce-eager")
232
+ common_args.append("-cc.cudagraph_mode=none")
233
if runner != "auto":
234
common_args.extend(["--runner", runner])
235
if trust_remote_code: