Define embedding_4bit ops

larryliu0820 · larryliu0820 · commit d504a61c12a7 · 2024-04-18T20:52:38.000-07:00
Summary:

Test Plan:

Reviewers:

Subscribers:

Tasks:

Tags:
diff --git a/exir/passes/_quant_patterns_and_replacements.py b/exir/passes/_quant_patterns_and_replacements.py
@@ -189,7 +189,7 @@ def embedding_byte_dtype_out_meta(
 
 quantized_decomposed_lib.define(
     "embedding_4bit.dtype_out(Tensor weight, Tensor weight_scales, Tensor? weight_zero_points, "
-    "int weight_quant_min, int weight_quant_max, Tensor indices, ScalarType? dtype=None, *, Tensor(a!) out) -> Tensor(a!)",
+    "int weight_quant_min, int weight_quant_max, Tensor indices, *, ScalarType? dtype=None, Tensor(a!) out) -> Tensor(a!)",
 )
 
 

Original file line number	Diff line number	Diff line change
`@@ -189,7 +189,7 @@ def embedding_byte_dtype_out_meta(`
`189`	`189`
`190`	`190`	`quantized_decomposed_lib.define(`
`191`	`191`	`"embedding_4bit.dtype_out(Tensor weight, Tensor weight_scales, Tensor? weight_zero_points, "`
`192`		`- "int weight_quant_min, int weight_quant_max, Tensor indices, ScalarType? dtype=None, *, Tensor(a!) out) -> Tensor(a!)",`
	`192`	`+ "int weight_quant_min, int weight_quant_max, Tensor indices, *, ScalarType? dtype=None, Tensor(a!) out) -> Tensor(a!)",`
`193`	`193`	`)`
`194`	`194`
`195`	`195`