We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 2607f0d commit cfd3e91Copy full SHA for cfd3e91
vec_inf/multinode_vllm.slurm
@@ -117,6 +117,7 @@ if [ "$VENV_BASE" = "singularity" ]; then
117
--max-logprobs ${MAX_LOGPROBS} \
118
--max-model-len ${MAX_MODEL_LEN} \
119
--max-num-seqs ${MAX_NUM_SEQS} \
120
+ --gpu-memory-utilization ${GPU_MEMORY_UTILIZATION} \
121
--max-num-batched-tokens ${MAX_NUM_BATCHED_TOKENS} \
122
--compilation-config ${COMPILATION_CONFIG} \
123
--task ${TASK} \
0 commit comments