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 7, 07:45 UTC
[Rocm][CI] Fix ROCm LM Eval Large Models (8 Card) (#35913)
Signed-off-by: charlifu <charlifu@amd.com>
Charlie Fu committed
Mar 3, 2026 at 22:50 UTC
3c85cd9d74627735413065c40676205085d76085
1 file changed
-1
.buildkite/lm-eval-harness/configs/models-large-rocm.txt
-1
@@ -1,2 +1 @@
1
Meta-Llama-4-Maverick-17B-128E-Instruct-FP8.yaml
2
-Qwen3-235B-A22B-Instruct-2507-FP8.yaml