Doc updates

microsoft · Mar 4, 2024 · 1e702a8 · 1e702a8
1 parent 9759369
commit 1e702a8
Show file tree

Hide file tree

Showing 3 changed files with 3 additions and 2 deletions.
diff --git a/docs/OperatorKernels.md b/docs/OperatorKernels.md
@@ -1271,6 +1271,7 @@ Do not modify directly.*
 |MatMulIntegerToFloat|*in* A:**T1**<br> *in* B:**T2**<br> *in* a_scale:**T3**<br> *in* b_scale:**T3**<br> *in* a_zero_point:**T1**<br> *in* b_zero_point:**T2**<br> *in* bias:**T3**<br> *out* Y:**T3**|1+|**T1** = tensor(int8), tensor(uint8)<br/> **T2** = tensor(int8), tensor(uint8)<br/> **T3** = tensor(float), tensor(float16)|
 |MultiHeadAttention|*in* query:**T**<br> *in* key:**T**<br> *in* value:**T**<br> *in* bias:**T**<br> *in* key_padding_mask:**M**<br> *in* relative_position_bias:**T**<br> *in* past_key:**T**<br> *in* past_value:**T**<br> *out* output:**T**<br> *out* present_key:**T**<br> *out* present_value:**T**|1+|**M** = tensor(int32)<br/> **T** = tensor(float), tensor(float16)|
 |NhwcConv|*in* X:**T**<br> *in* W:**T**<br> *in* B:**T**<br> *out* Y:**T**|1+|**T** = tensor(float), tensor(float16)|
+|QAttention|*in* input:**T1**<br> *in* weight:**T2**<br> *in* bias:**T3**<br> *in* input_scale:**T3**<br> *in* weight_scale:**T3**<br> *in* mask_index:**T4**<br> *in* input_zero_point:**T1**<br> *in* weight_zero_point:**T2**<br> *in* past:**T3**<br> *out* output:**T3**<br> *out* present:**T3**|1+|**T1** = tensor(int8), tensor(uint8)<br/> **T2** = tensor(int8), tensor(uint8)<br/> **T3** = tensor(float), tensor(float16)<br/> **T4** = tensor(int32)|
 |QLinearAdd|*in* A:**T**<br> *in* A_scale:**tensor(float)**<br> *in* A_zero_point:**T**<br> *in* B:**T**<br> *in* B_scale:**tensor(float)**<br> *in* B_zero_point:**T**<br> *in* C_scale:**tensor(float)**<br> *in* C_zero_point:**T**<br> *out* C:**T**|1+|**T** = tensor(int8), tensor(uint8)|
 |QLinearAveragePool|*in* X:**T**<br> *in* x_scale:**tensor(float)**<br> *in* x_zero_point:**T**<br> *in* y_scale:**tensor(float)**<br> *in* y_zero_point:**T**<br> *out* Y:**T**|1+|**T** = tensor(int8), tensor(uint8)|
 |QLinearConcat|*in* Y_scale:**TF**<br> *in* Y_zero_point:**T8**<br> *in* inputs:**TV**<br> *out* Y:**T8**|1+|**T8** = tensor(int8), tensor(uint8)<br/> **TF** = tensor(float)<br/> **TV** = tensor(float), tensor(int8), tensor(uint8)|

diff --git a/onnxruntime/core/providers/dml/DmlExecutionProvider/src/Operators/DmlOperatorQAttention.cpp b/onnxruntime/core/providers/dml/DmlExecutionProvider/src/Operators/DmlOperatorQAttention.cpp
@@ -666,7 +666,7 @@ class DmlOperatorQAttention : public DmlOperator
         operatorGraphDesc.outputEdgeCount = gsl::narrow_cast<uint32_t>(outputEdges.size());
         operatorGraphDesc.outputEdges = outputEdges.data();
         operatorGraphDesc.nodeCount = gsl::narrow_cast<uint32_t>(opDescs.size());
-        operatorGraphDesc.nodesAsOpDesc = opDescs.data();
+        operatorGraphDesc.nodes = opDescs.data();
 
         SetDmlOperatorGraphDesc(std::move(operatorGraphDesc), kernelCreationContext);
     }

diff --git a/onnxruntime/test/contrib_ops/quantize_attention_op_test.cc b/onnxruntime/test/contrib_ops/quantize_attention_op_test.cc
@@ -911,7 +911,7 @@ void TestQuantizedAttentionPastState(int64_t batch,
   std::vector<int64_t> input_dims{batch, seq_len, hidden_size};
   std::vector<InputT> input_data = random.Gaussian<InputT>(input_dims, input_mean, static_cast<InputT>(input_range / 6), input_min, input_max);
 
-  constexpr WeightT weight_min = constexpr(std::is_same_v<WeightT, int8_t>) ? std::numeric_limits<int8_t>::min() / 2 : std::numeric_limits<WeightT>::min();
+  constexpr WeightT weight_min = std::is_same_v<WeightT, int8_t> ? std::numeric_limits<int8_t>::min() / 2 : std::numeric_limits<WeightT>::min();
   constexpr WeightT weight_max = std::numeric_limits<WeightT>::max() / 2;
   constexpr int32_t weight_range = weight_max - weight_min;