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
50
50
51
51
if [ -n " $max_num_seqs " ]; then
52
52
export VLLM_MAX_NUM_SEQS=$max_num_seqs
53
- else
53
+ else
54
54
export VLLM_MAX_NUM_SEQS=256
55
55
fi
56
56
75
75
mkdir -p $LOG_DIR
76
76
77
77
# Model and entrypoint configuration. API Server URL (host, port) are set automatically based on the
78
- # SLURM job
78
+ # SLURM job
79
79
export SRC_DIR=" $( dirname " $0 " ) "
80
80
export MODEL_DIR=" ${SRC_DIR} /models/${MODEL_FAMILY} "
81
81
Original file line number Diff line number Diff line change @@ -200,4 +200,4 @@ More profiling metrics coming soon!
200
200
201
201
| Variant | Suggested resource allocation | Avg prompt throughput | Avg generation throughput |
202
202
| :----------:| :----------:| :----------:| :----------:|
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