Update hf_quant_config.json (#2)

- Update hf_quant_config.json (7f7fd49789974079affecf5eaa06d6308250e930)

Co-authored-by: Baseten Admin <[email protected]>

Files changed (1) hide show

hf_quant_config.json CHANGED Viewed

@@ -5,7 +5,7 @@
     },
     "quantization": {
         "quant_algo": "NVFP4",
-        "kv_cache_quant_algo": "FP8",
         "group_size": 16,
         "exclude_modules": [
             "lm_head",

     },
     "quantization": {
         "quant_algo": "NVFP4",
+        "kv_cache_quant_algo": null,
         "group_size": 16,
         "exclude_modules": [
             "lm_head",