From f7530ff36be31ed7fc2e182806023845a4ec6a06 Mon Sep 17 00:00:00 2001 From: electriclilies Date: Wed, 29 Jul 2020 18:03:21 -0700 Subject: [PATCH 1/2] updated hybridscript docs and pass infra docs --- docs/dev/hybrid_script.rst | 7 +++++++ docs/dev/relay_pass_infra.rst | 2 +- 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/docs/dev/hybrid_script.rst b/docs/dev/hybrid_script.rst index 7bb5e234cba0..86e8e0718298 100644 --- a/docs/dev/hybrid_script.rst +++ b/docs/dev/hybrid_script.rst @@ -91,3 +91,10 @@ Math Intrinsics So far, these math intrinsics, ``log``, ``exp``, ``sigmoid``, ``tanh``, ``power``, and ``popcount``, are supported. Math intrinsics will be imported by the decorator. Most of the intrinsics are borrowed by library implementation except ``popcount`` and ``sigmoid``. I implemented them manually. + + +Casting +~~~~~~~ + +You can cast values by using the keywords``uint8``, ``uint32``, ``uint64``, ``int8``, ``int16``, ``int32``, ``int64``, +``float16``, ``float32``, ``float64``. \ No newline at end of file diff --git a/docs/dev/relay_pass_infra.rst b/docs/dev/relay_pass_infra.rst index 446a91bceff7..15487ac0227c 100644 --- a/docs/dev/relay_pass_infra.rst +++ b/docs/dev/relay_pass_infra.rst @@ -612,7 +612,7 @@ sequential pass example could be like the following to enable IR dumping for seq = tvm.transform.Sequential([ relay.transform.InferType(), relay.transform.FoldConstant(), - transform.PrintIR(), + ir.transform.PrintIR(), relay.transform.EliminateCommonSubexpr(), relay.transform.AlterOpLayout() ]) From a68ceb78c984945fdfedc3162aef974ac0b8ad13 Mon Sep 17 00:00:00 2001 From: Lily Orth-Smith Date: Thu, 30 Jul 2020 10:57:33 -0700 Subject: [PATCH 2/2] forgot uint16 --- docs/dev/hybrid_script.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/dev/hybrid_script.rst b/docs/dev/hybrid_script.rst index 86e8e0718298..939cf05bac6e 100644 --- a/docs/dev/hybrid_script.rst +++ b/docs/dev/hybrid_script.rst @@ -96,5 +96,5 @@ except ``popcount`` and ``sigmoid``. I implemented them manually. Casting ~~~~~~~ -You can cast values by using the keywords``uint8``, ``uint32``, ``uint64``, ``int8``, ``int16``, ``int32``, ``int64``, -``float16``, ``float32``, ``float64``. \ No newline at end of file +You can cast values by using the keywords ``uint8``, ``uint16`` ``uint32``, ``uint64``, ``int8``, ``int16``, ``int32``, ``int64``, +``float16``, ``float32``, ``float64``.