Update hf_quant_config.json
#2
by
baseten-admin
- opened
- hf_quant_config.json +1 -1
hf_quant_config.json
CHANGED
|
@@ -5,7 +5,7 @@
|
|
| 5 |
},
|
| 6 |
"quantization": {
|
| 7 |
"quant_algo": "NVFP4",
|
| 8 |
-
"kv_cache_quant_algo":
|
| 9 |
"group_size": 16,
|
| 10 |
"exclude_modules": [
|
| 11 |
"lm_head",
|
|
|
|
| 5 |
},
|
| 6 |
"quantization": {
|
| 7 |
"quant_algo": "NVFP4",
|
| 8 |
+
"kv_cache_quant_algo": null,
|
| 9 |
"group_size": 16,
|
| 10 |
"exclude_modules": [
|
| 11 |
"lm_head",
|