[Mlir-commits] [mlir] Sub-channel quantized type implementation (PR #120172)

Kevin Gleason llvmlistbot at llvm.org
Tue Feb 11 14:55:22 PST 2025


================
@@ -64,3 +64,12 @@ module @parseUniformPerAxisMixed attributes {
   bytecode.test = !quant.uniform<i8:f32:1, {2.0e+2,0.99872:120}>
 } {}
 
+//===----------------------------------------------------------------------===//
+// UniformQuantizedSubChannel
+//===----------------------------------------------------------------------===//
+
+// CHECK-LABEL: parseUniformSubChannel
+module @parseUniformSubChannel attributes {
+  // CHECK: !quant.uniform<i8:f32:{0:1,1:2}, {{\{}}{2.000000e+00:10, 3.000000e+00:20}, {4.000000e+00:30, 5.000000e+00:40}}>
+  bytecode.test = !quant.uniform<i8:f32:{0:1, 1:2}, {{2.0:10, 3.0:20}, {4.0:30, 5.0:40}}>
+} {}
----------------
GleasonK wrote:

newline EOF

https://github.com/llvm/llvm-project/pull/120172


More information about the Mlir-commits mailing list