File tree Expand file tree Collapse file tree 2 files changed +3
-3
lines changed Expand file tree Collapse file tree 2 files changed +3
-3
lines changed Original file line number Diff line number Diff line change @@ -50,7 +50,7 @@ export MODEL_WEIGHTS_PARENT_DIR=$model_weights_parent_dir
5050
5151if [ -n " $max_num_seqs " ]; then
5252 export VLLM_MAX_NUM_SEQS=$max_num_seqs
53- else
53+ else
5454 export VLLM_MAX_NUM_SEQS=256
5555fi
5656
7575mkdir -p $LOG_DIR
7676
7777# Model and entrypoint configuration. API Server URL (host, port) are set automatically based on the
78- # SLURM job
78+ # SLURM job
7979export SRC_DIR=" $( dirname " $0 " ) "
8080export MODEL_DIR=" ${SRC_DIR} /models/${MODEL_FAMILY} "
8181
Original file line number Diff line number Diff line change @@ -200,4 +200,4 @@ More profiling metrics coming soon!
200200
201201| Variant | Suggested resource allocation | Avg prompt throughput | Avg generation throughput |
202202| :----------:| :----------:| :----------:| :----------:|
203- | [ ` Qwen2.5-Math-RM-72B ` ] ( https://huggingface.co/Qwen/Qwen2.5-Math-RM-72B ) | 4x a40 | - tokens/s | - tokens/s |
203+ | [ ` Qwen2.5-Math-RM-72B ` ] ( https://huggingface.co/Qwen/Qwen2.5-Math-RM-72B ) | 4x a40 | - tokens/s | - tokens/s |
You can’t perform that action at this time.
0 commit comments