Sfoglia il codice sorgente

perf(inference): adjust batch ratio for GPU memory sizes

- Simplify batch ratio logic for GPU memory >= 16GB
- Remove unnecessary conditions for 20GB and 40GB memory
myhloli 8 mesi fa
parent
commit
58b6ad8ca2
1 ha cambiato i file con 1 aggiunte e 3 eliminazioni
  1. 1 3
      magic_pdf/model/doc_analyze_by_custom_model.py

+ 1 - 3
magic_pdf/model/doc_analyze_by_custom_model.py

@@ -170,9 +170,7 @@ def doc_analyze(
         gpu_memory = int(os.getenv("VIRTUAL_VRAM_SIZE", round(get_vram(device))))
         if gpu_memory is not None and gpu_memory >= 8:
 
-            if gpu_memory >= 16:
-                batch_ratio = 8
-            elif gpu_memory >= 10:
+            if gpu_memory >= 10:
                 batch_ratio = 4
             else:
                 batch_ratio = 2