Skip to content

Commit

Permalink
Remove marlin warning (vllm-project#4918)
Browse files Browse the repository at this point in the history
  • Loading branch information
alexm-neuralmagic authored and joerunde committed May 20, 2024
1 parent 2cc299f commit c23600a
Showing 1 changed file with 0 additions and 4 deletions.
4 changes: 0 additions & 4 deletions csrc/quantization/gptq_marlin/gptq_marlin.cu
Original file line number Diff line number Diff line change
Expand Up @@ -1519,10 +1519,6 @@ exec_config_t determine_thread_config(int prob_m, int prob_n, int prob_k,
}
}

printf("WARNING: Marlin kernel is reducing max_m_blocks due to small SM "
"GPU cache. This may "
"hurt performance. Consider upgrading your GPU.\n");

max_m_blocks--; // Process less M blocks per invocation to reduce cache
// usage
}
Expand Down

0 comments on commit c23600a

Please sign in to comment.