Add missing quant_config.json for compatibility with vLLM backends out of the box. (#1)

- Add missing quant_config.json for compatibility with vLLM backends out of the box. (aa2a3bfa23cced5784ce861bac33972e542ceed9)


Co-authored-by: Vaclav Kosar <[email protected]>

quant_config.json

@@ -0,0 +1,6 @@
+{
+    "zero_point": true,
+    "q_group_size": 128,
+    "w_bit": 4,
+    "version": "GEMM"
+}