Remove marlin warning (#4918)

vllm-project · May 20, 2024 · da5a0b5 · da5a0b5
1 parent 6287537
commit da5a0b5
Showing 1 changed file with 0 additions and 4 deletions.
diff --git a/csrc/quantization/gptq_marlin/gptq_marlin.cu b/csrc/quantization/gptq_marlin/gptq_marlin.cu
@@ -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
   }