Remove marlin warning (#4918)

da5a0b53 · Alexander Matveev · GitHub · 6287537a · da5a0b53
Unverified Commit da5a0b53 authored May 20, 2024 by Alexander Matveev Committed by GitHub May 20, 2024
Show whitespace changes
Inline Side-by-side

Showing with 0 additions and 4 deletions

csrc/quantization/gptq_marlin/gptq_marlin.cu csrc/quantization/gptq_marlin/gptq_marlin.cu +0 -4

No files found.
--- 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
  }