Gemma4-VL: add gemma4_e2b_qat_vl_decode_int4linsym

.gitattributes

@@ -67,3 +67,5 @@ ios-frontend/gemma4_qat_gather_raw/embed_tokens.scale.f32 filter=lfs diff=lfs me
 ios-frontend/gemma4_qat_gather_raw/proj.f32 filter=lfs diff=lfs merge=lfs -text
 gpu-pipelined/gemma4_e2b_qat_vl_decode_int4linsym_tbl/gemma4_e2b_qat_vl_decode_int4linsym_tbl.aimodel/main.mlirb filter=lfs diff=lfs merge=lfs -text
 gpu-pipelined/gemma4_e2b_qat_vl_decode_int4linsym_tbl/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gpu-pipelined/gemma4_e2b_qat_vl_decode_int4linsym/gemma4_e2b_qat_vl_decode_int4linsym.aimodel/main.mlirb filter=lfs diff=lfs merge=lfs -text
+gpu-pipelined/gemma4_e2b_qat_vl_decode_int4linsym/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text

gpu-pipelined/gemma4_e2b_qat_vl_decode_int4linsym/gemma4_e2b_qat_vl_decode_int4linsym.aimodel/main.hash

@@ -0,0 +1 @@
+�Q��/���#�6��-$����v2��#64�5

gpu-pipelined/gemma4_e2b_qat_vl_decode_int4linsym/gemma4_e2b_qat_vl_decode_int4linsym.aimodel/main.mlirb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c95194a02ffeb5f2239336d5cc2d240c96fd82c40f763204e2cb233634893506
+size 2088901565

gpu-pipelined/gemma4_e2b_qat_vl_decode_int4linsym/gemma4_e2b_qat_vl_decode_int4linsym.aimodel/metadata.json

@@ -0,0 +1,3 @@
+{
+  "assetVersion" : "2.0"
+}

gpu-pipelined/gemma4_e2b_qat_vl_decode_int4linsym/metadata.json

@@ -0,0 +1,28 @@
+{
+  "metadata_version": "0.2",
+  "kind": "llm",
+  "name": "gemma4_e2b_qat_vl_decode_int4linsym",
+  "assets": {
+    "main": "gemma4_e2b_qat_vl_decode_int4linsym.aimodel"
+  },
+  "language": {
+    "tokenizer": "google/gemma-4-E2B-it-qat-q4_0-unquantized",
+    "vocab_size": 262144,
+    "max_context_length": 4096,
+    "embedded_tokenizer": true,
+    "function_map": {
+      "main": [
+        "main"
+      ]
+    }
+  },
+  "source": {
+    "model_definition": "torch",
+    "hf_model_id": "google/gemma-4-E2B-it-qat-q4_0-unquantized"
+  },
+  "compression": null,
+  "compilation": {
+    "date": "2026-06-12T05:32:04.604393+00:00",
+    "targets": []
+  }
+}

gpu-pipelined/gemma4_e2b_qat_vl_decode_int4linsym/tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
+size 32169626

gpu-pipelined/gemma4_e2b_qat_vl_decode_int4linsym/tokenizer/tokenizer_config.json

@@ -0,0 +1,96 @@
+{
+  "audio_token": "<|audio|>",
+  "backend": "tokenizers",
+  "boa_token": "<|audio>",
+  "boi_token": "<|image>",
+  "bos_token": "<bos>",
+  "eoa_token": "<audio|>",
+  "eoc_token": "<channel|>",
+  "eoi_token": "<image|>",
+  "eos_token": "<eos>",
+  "eot_token": "<turn|>",
+  "escape_token": "<|\"|>",
+  "etc_token": "<tool_call|>",
+  "etd_token": "<tool|>",
+  "etr_token": "<tool_response|>",
+  "extra_special_tokens": [
+    "<|video|>"
+  ],
+  "image_token": "<|image|>",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "audio_token": "<|audio|>",
+    "boa_token": "<|audio>",
+    "boi_token": "<|image>",
+    "eoa_token": "<audio|>",
+    "eoc_token": "<channel|>",
+    "eoi_token": "<image|>",
+    "eot_token": "<turn|>",
+    "escape_token": "<|\"|>",
+    "etc_token": "<tool_call|>",
+    "etd_token": "<tool|>",
+    "etr_token": "<tool_response|>",
+    "image_token": "<|image|>",
+    "soc_token": "<|channel>",
+    "sot_token": "<|turn>",
+    "stc_token": "<|tool_call>",
+    "std_token": "<|tool>",
+    "str_token": "<|tool_response>",
+    "think_token": "<|think|>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "processor_class": "Gemma4Processor",
+  "response_schema": {
+    "properties": {
+      "content": {
+        "type": "string"
+      },
+      "role": {
+        "const": "assistant"
+      },
+      "thinking": {
+        "type": "string"
+      },
+      "tool_calls": {
+        "items": {
+          "properties": {
+            "function": {
+              "properties": {
+                "arguments": {
+                  "additionalProperties": {},
+                  "type": "object",
+                  "x-parser": "gemma4-tool-call"
+                },
+                "name": {
+                  "type": "string"
+                }
+              },
+              "type": "object",
+              "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
+            },
+            "type": {
+              "const": "function"
+            }
+          },
+          "type": "object"
+        },
+        "type": "array",
+        "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
+      }
+    },
+    "type": "object",
+    "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|tool_response\\>)?"
+  },
+  "soc_token": "<|channel>",
+  "sot_token": "<|turn>",
+  "stc_token": "<|tool_call>",
+  "std_token": "<|tool>",
+  "str_token": "<|tool_response>",
+  "think_token": "<|think|>",
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>"
+}