From 4ff61ababa25f4a519185013c9cce00142341f04 Mon Sep 17 00:00:00 2001
From: QiliangCui <derrhein@gmail.com>
Date: Wed, 2 Jul 2025 23:46:41 -0700
Subject: [PATCH] [TPU] Add a case to cover
 RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a8 (#20385)

Signed-off-by: Qiliang Cui <derrhein@gmail.com>
---
 .buildkite/scripts/tpu/quantized_v6e_1.env | 14 ++++++++++++++
 1 file changed, 14 insertions(+)
 create mode 100644 .buildkite/scripts/tpu/quantized_v6e_1.env

diff --git a/.buildkite/scripts/tpu/quantized_v6e_1.env b/.buildkite/scripts/tpu/quantized_v6e_1.env
new file mode 100644
index 0000000000000..bab34b3be3b9a
--- /dev/null
+++ b/.buildkite/scripts/tpu/quantized_v6e_1.env
@@ -0,0 +1,14 @@
+# Environment config
+TEST_NAME=llama8bw8a8
+CONTAINER_NAME=vllm-tpu
+
+# vllm config
+MODEL=RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a8
+MAX_NUM_SEQS=128
+MAX_NUM_BATCHED_TOKENS=1024
+TENSOR_PARALLEL_SIZE=1
+MAX_MODEL_LEN=2048
+DOWNLOAD_DIR=/mnt/disks/persist
+EXPECTED_THROUGHPUT=10.0
+INPUT_LEN=1800
+OUTPUT_LEN=128