[Mlir-commits] [mlir] QuantileType relax quantileType conditions and inheritance issue (PR #204793)

[llvmlistbot at llvm.org]

https://github.com/vsimion26 created https://github.com/llvm/llvm-project/pull/204793

None

>From 93b68513b07523054a23d100069f2722d81953ec Mon Sep 17 00:00:00 2001
From: vsimion26 <vlad.simion at intel.com>
Date: Fri, 19 Jun 2026 11:32:13 +0100
Subject: [PATCH] QuantileType relax quantileType conditions and inheritance

---
 mlir/include/mlir/Dialect/Quant/IR/QuantTypes.h     | 10 +++++-----
 mlir/lib/Dialect/Quant/IR/QuantTypes.cpp            |  8 +++++---
 mlir/test/Dialect/Quant/invalid-quantile-types.mlir |  4 ++--
 3 files changed, 12 insertions(+), 10 deletions(-)

diff --git a/mlir/include/mlir/Dialect/Quant/IR/QuantTypes.h b/mlir/include/mlir/Dialect/Quant/IR/QuantTypes.h
index 2001178d5939c..98c912024a6a7 100644
--- a/mlir/include/mlir/Dialect/Quant/IR/QuantTypes.h
+++ b/mlir/include/mlir/Dialect/Quant/IR/QuantTypes.h
@@ -551,13 +551,14 @@ class CalibratedQuantizedType
 /*Syntax:
 
     ```
-    quantile-type ::= `!quant.quantile` `<` type `:` type `,` `{` float-list `}`
+    quantile-type ::= `!quant.quantile` `<` type `:` type `,` `{` float-list /
+   int-list `}`
    (`,` `<` int `,` int `>`)? `>`
     ```
 
     A quantile type represents a quantile-based floating point encoding, where
-    discrete storage values are totally defined by the floating-point values
-   entries in a quantile lookup table of F8/F16/F32/F64.
+    discrete storage values are totally defined by the floating-point or integer
+   values entries in a quantile lookup table of F8/F16/F32/F64 or integer types.
 
     Optionally, explicit minimum and maximum storage values can be specified
     after the LUT as `<min:max>`.
@@ -587,8 +588,7 @@ class CalibratedQuantizedType
 */
 
 class QuantileType
-    : public Type::TypeBase<QuantileType, QuantizedType,
-                            detail::QuantileTypeStorage,
+    : public Type::TypeBase<QuantileType, Type, detail::QuantileTypeStorage,
                             mlir::QuantStorageTypeInterface::Trait> {
 public:
   using ImplType = detail::QuantileTypeStorage;
diff --git a/mlir/lib/Dialect/Quant/IR/QuantTypes.cpp b/mlir/lib/Dialect/Quant/IR/QuantTypes.cpp
index c150c151e1e11..adabb49aea003 100644
--- a/mlir/lib/Dialect/Quant/IR/QuantTypes.cpp
+++ b/mlir/lib/Dialect/Quant/IR/QuantTypes.cpp
@@ -41,7 +41,8 @@ unsigned QuantizedType::getFlags() const {
 }
 
 bool QuantizedType::classof(Type type) {
-  return llvm::isa<QuantDialect>(type.getDialect());
+  return llvm::isa<QuantDialect>(type.getDialect()) &&
+         !llvm::isa<QuantileType>(type);
 }
 
 LogicalResult
@@ -578,8 +579,9 @@ LogicalResult QuantileType::verifyInvariants(
     std::optional<int64_t> storageMin, std::optional<int64_t> storageMax) {
   if (!storageType.isIntOrFloat())
     return emitError() << "storage type must be an integer or float type";
-  if (!llvm::isa<mlir::FloatType>(quantileType))
-    return emitError() << "quantile type must be a float type";
+  if (!llvm::isa<mlir::FloatType>(quantileType) &&
+      !llvm::isa<mlir::IntegerType>(quantileType))
+    return emitError() << "quantile type must be a float or integer type";
   if (quantiles.empty())
     return emitError() << "quantile values must not be empty";
   if (storageMin.has_value() != storageMax.has_value())
diff --git a/mlir/test/Dialect/Quant/invalid-quantile-types.mlir b/mlir/test/Dialect/Quant/invalid-quantile-types.mlir
index faf16d01a9cd5..4a7703fd0e553 100644
--- a/mlir/test/Dialect/Quant/invalid-quantile-types.mlir
+++ b/mlir/test/Dialect/Quant/invalid-quantile-types.mlir
@@ -11,8 +11,8 @@ func.func private @invalid_storage_type() -> !quant.quantile<tensor<1xf32>:f32,
 // -----
 
 // Quantile (expressed) type must be a float.
-// expected-error @+1 {{quantile type must be a float type}}
-func.func private @invalid_quantile_type() -> !quant.quantile<ui4:i8, {1.0, 0.0, -1.0}>
+// expected-error @+1 {{quantile type must be a float or integer type}}
+func.func private @invalid_quantile_type() -> !quant.quantile<ui4:tensor<1xf32>, {1.0, 0.0, -1.0}>
 
 // -----