Skip to content

Commit 0149ee8

Browse files
jambaykjambayk
authored
QNN Recipes: Remove extra_options (microsoft#149)
1 parent bdf7b86 commit 0149ee8

12 files changed

Lines changed: 12 additions & 34 deletions

File tree

‎Qwen-Qwen2.5-1.5B-Instruct/QNN/config.json‎

Lines changed: 1 addition & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -74,8 +74,7 @@
7474
"calibration_providers": [ "CUDAExecutionProvider" ],
7575
"quant_preprocess": true,
7676
"op_types_to_exclude": [ "GatherBlockQuantized", "GroupQueryAttention", "MatMulNBits" ],
77-
"save_as_external_data": true,
78-
"extra_options": { "CalibStridedMinMax": 4 }
77+
"save_as_external_data": true
7978
},
8079
"sp": { "type": "SplitModel" },
8180
"st": { "type": "StaticLLM", "batch_size": 1, "context_length": 64 },

‎Qwen-Qwen2.5-1.5B-Instruct/aitk/qwen2_5_qnn_config.json‎

Lines changed: 1 addition & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -112,10 +112,7 @@
112112
"GroupQueryAttention",
113113
"MatMulNBits"
114114
],
115-
"save_as_external_data": true,
116-
"extra_options": {
117-
"CalibStridedMinMax": 4
118-
}
115+
"save_as_external_data": true
119116
},
120117
"sp": {
121118
"type": "SplitModel"

‎Qwen-Qwen2.5-7B-Instruct/QNN/config.json‎

Lines changed: 1 addition & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -74,8 +74,7 @@
7474
"calibration_providers": [ "CUDAExecutionProvider" ],
7575
"quant_preprocess": true,
7676
"op_types_to_exclude": [ "GatherBlockQuantized", "GroupQueryAttention", "MatMulNBits" ],
77-
"save_as_external_data": true,
78-
"extra_options": { "CalibStridedMinMax": 4 }
77+
"save_as_external_data": true
7978
},
8079
"sp": { "type": "SplitModel" },
8180
"st": { "type": "StaticLLM", "batch_size": 1, "context_length": 64 },

‎deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B/aitk/deepseek_qnn_config.json‎

Lines changed: 1 addition & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -112,10 +112,7 @@
112112
"GroupQueryAttention",
113113
"MatMulNBits"
114114
],
115-
"save_as_external_data": true,
116-
"extra_options": {
117-
"CalibStridedMinMax": 4
118-
}
115+
"save_as_external_data": true
119116
},
120117
"sp": {
121118
"type": "SplitModel"

‎meta-llama-Llama-3.1-8B-Instruct/QNN/config.json‎

Lines changed: 1 addition & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -74,8 +74,7 @@
7474
"calibration_providers": [ "CUDAExecutionProvider" ],
7575
"quant_preprocess": true,
7676
"op_types_to_exclude": [ "GatherBlockQuantized", "GroupQueryAttention", "MatMulNBits" ],
77-
"save_as_external_data": true,
78-
"extra_options": { "CalibStridedMinMax": 4 }
77+
"save_as_external_data": true
7978
},
8079
"sp": { "type": "SplitModel" },
8180
"st": { "type": "StaticLLM", "batch_size": 1, "context_length": 64 },

‎meta-llama-Llama-3.1-8B-Instruct/aitk/llama3_1_qnn_config.json‎

Lines changed: 1 addition & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -112,10 +112,7 @@
112112
"GroupQueryAttention",
113113
"MatMulNBits"
114114
],
115-
"save_as_external_data": true,
116-
"extra_options": {
117-
"CalibStridedMinMax": 4
118-
}
115+
"save_as_external_data": true
119116
},
120117
"sp": {
121118
"type": "SplitModel"

‎meta-llama-Llama-3.2-1B-Instruct/aitk/llama3_2_qnn_config.json‎

Lines changed: 1 addition & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -112,10 +112,7 @@
112112
"GroupQueryAttention",
113113
"MatMulNBits"
114114
],
115-
"save_as_external_data": true,
116-
"extra_options": {
117-
"CalibStridedMinMax": 4
118-
}
115+
"save_as_external_data": true
119116
},
120117
"sp": {
121118
"type": "SplitModel"

‎microsoft-Phi-3-mini-128k-instruct/QNN/config.json‎

Lines changed: 1 addition & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -74,8 +74,7 @@
7474
"calibration_providers": [ "CUDAExecutionProvider" ],
7575
"quant_preprocess": true,
7676
"op_types_to_exclude": [ "GatherBlockQuantized", "GroupQueryAttention", "MatMulNBits" ],
77-
"save_as_external_data": true,
78-
"extra_options": { "CalibStridedMinMax": 4 }
77+
"save_as_external_data": true
7978
},
8079
"sp": { "type": "SplitModel" },
8180
"st": { "type": "StaticLLM", "batch_size": 1, "context_length": 64 },

‎microsoft-Phi-3-mini-4k-instruct/QNN/config.json‎

Lines changed: 1 addition & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -74,8 +74,7 @@
7474
"calibration_providers": [ "CUDAExecutionProvider" ],
7575
"quant_preprocess": true,
7676
"op_types_to_exclude": [ "GatherBlockQuantized", "GroupQueryAttention", "MatMulNBits" ],
77-
"save_as_external_data": true,
78-
"extra_options": { "CalibStridedMinMax": 4 }
77+
"save_as_external_data": true
7978
},
8079
"sp": { "type": "SplitModel" },
8180
"st": { "type": "StaticLLM", "batch_size": 1, "context_length": 64 },

‎microsoft-Phi-3.5-mini-instruct/QNN/config.json‎

Lines changed: 1 addition & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -72,8 +72,7 @@
7272
"calibration_providers": [ "CUDAExecutionProvider" ],
7373
"quant_preprocess": true,
7474
"op_types_to_exclude": [ "GatherBlockQuantized", "GroupQueryAttention", "MatMulNBits" ],
75-
"save_as_external_data": true,
76-
"extra_options": { "CalibStridedMinMax": 4 }
75+
"save_as_external_data": true
7776
},
7877
"sp": { "type": "SplitModel" },
7978
"st": { "type": "StaticLLM", "batch_size": 1, "context_length": 64 },

0 commit comments

Comments
 (0)