[TPU] Add a case to cover RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a8 (#20385)
Signed-off-by: Qiliang Cui <derrhein@gmail.com>
This commit is contained in:
@@ -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
|
||||
Reference in New Issue
Block a user