[models-hub] Update llm:gemma-4

qinxuye · qinxuye · commit b15bb5147c13 · 2026-04-12T12:07:23.000+08:00
diff --git a/xinference/model/llm/llm_family.json b/xinference/model/llm/llm_family.json
@@ -29821,6 +29821,24 @@
           }
         }
       },
+      {
+        "model_size_in_billions": 31,
+        "model_format": "fp4",
+        "model_src": {
+          "huggingface": {
+            "model_id": "nvidia/Gemma-4-31B-IT-NVFP4",
+            "quantizations": [
+              "FP4"
+            ]
+          },
+          "modelscope": {
+            "model_id": "nv-community/Gemma-4-31B-IT-NVFP4",
+            "quantizations": [
+              "FP4"
+            ]
+          }
+        }
+      },
       {
         "model_size_in_billions": 26,
         "model_format": "pytorch",
@@ -30212,6 +30230,6 @@
       ]
     },
     "featured": true,
-    "updated_at": 1775810942
+    "updated_at": 1775834800
   }
 ]

Original file line number	Diff line number	Diff line change
`@@ -29821,6 +29821,24 @@`
`29821`	`29821`	`}`
`29822`	`29822`	`}`
`29823`	`29823`	`},`
	`29824`	`+ {`
	`29825`	`+ "model_size_in_billions": 31,`
	`29826`	`+ "model_format": "fp4",`
	`29827`	`+ "model_src": {`
	`29828`	`+ "huggingface": {`
	`29829`	`+ "model_id": "nvidia/Gemma-4-31B-IT-NVFP4",`
	`29830`	`+ "quantizations": [`
	`29831`	`+ "FP4"`
	`29832`	`+ ]`
	`29833`	`+ },`
	`29834`	`+ "modelscope": {`
	`29835`	`+ "model_id": "nv-community/Gemma-4-31B-IT-NVFP4",`
	`29836`	`+ "quantizations": [`
	`29837`	`+ "FP4"`
	`29838`	`+ ]`
	`29839`	`+ }`
	`29840`	`+ }`
	`29841`	`+ },`
`29824`	`29842`	`{`
`29825`	`29843`	`"model_size_in_billions": 26,`
`29826`	`29844`	`"model_format": "pytorch",`
`@@ -30212,6 +30230,6 @@`
`30212`	`30230`	`]`
`30213`	`30231`	`},`
`30214`	`30232`	`"featured": true,`
`30215`		`- "updated_at": 1775810942`
	`30233`	`+ "updated_at": 1775834800`
`30216`	`30234`	`}`
`30217`	`30235`	`]`