[ROCm][CI] Use vLLM generation defaults for DeepSeek prefetch-offload eval (#41575)

Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-05-06 01:08:12 +00:00
parent 1333864408
commit 4a8ae26e53
1 changed files with 1 additions and 0 deletions
@@ -51,6 +51,7 @@ vllm serve "$MODEL" \
  --offload-num-in-group 2 \
  --offload-prefetch-step 1 \
  --offload-params w13_weight w2_weight \
+  --generation-config vllm \
  --port "$PORT" \
  ${EXTRA_ARGS+"${EXTRA_ARGS[@]}"} &
 SERVER_PID=$!