Explain how to generate module library in Quick Start tutorial (#323)

kevinthesun · tqchen · commit 452bcd5a548a · 2018-05-29T08:47:00.000-07:00
* Explain how to generate module library

* Small fix
diff --git a/nnvm/tutorials/define_and_compile_model.py b/nnvm/tutorials/define_and_compile_model.py
@@ -68,6 +68,9 @@
 # in an optimized runtime module for model serving.
 #
 # We'll first compile for Nvidia GPU.
+# To generate the module library, TVM will first transfer graph IR into lower
+# intrinsic IR for the specified target backend, which is CUDA in this example.
+# Then target backend will generate module library.
 
 opt_level = 0
 target = tvm.target.cuda()

Original file line number	Diff line number	Diff line change
`@@ -68,6 +68,9 @@`
`68`	`68`	`# in an optimized runtime module for model serving.`
`69`	`69`	`#`
`70`	`70`	`# We'll first compile for Nvidia GPU.`
	`71`	`+# To generate the module library, TVM will first transfer graph IR into lower`
	`72`	`+# intrinsic IR for the specified target backend, which is CUDA in this example.`
	`73`	`+# Then target backend will generate module library.`
`71`	`74`
`72`	`75`	`opt_level = 0`
`73`	`76`	`target = tvm.target.cuda()`