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 6, 07:00 UTC
[ROCm][CI] Update GSM8K eval config to use fp8-and-mixed models list (MI355) (#37721)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Andreas Karatzas committed
Mar 21, 2026 at 02:27 UTC
02eec7ecbefdb0d32e76e3c95a7426758369e5b2
1 file changed
+1
-1
.buildkite/test-amd.yaml
+1
-1
@@ -3572,7 +3572,7 @@ steps:
3572
- vllm/_aiter_ops.py
3573
- vllm/platforms/rocm.py
3574
commands:
3575
- - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-mi3xx-fp8.txt
3575
+ - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-mi3xx-fp8-and-mixed.txt
3576
3577
3578
- label: LM Eval Large Models (4 GPUs)(FP8) # TBD