From 7d40605c3abc23a34a56b1efa47e7d1256f853cb Mon Sep 17 00:00:00 2001 From: Varun Sharma Date: Fri, 16 Jun 2023 10:22:07 -0700 Subject: [PATCH 1/2] Add bind header Signed-off-by: Varun Sharma --- src/amdinfer/bindings/python/core/inference_response.cpp | 1 + 1 file changed, 1 insertion(+) diff --git a/src/amdinfer/bindings/python/core/inference_response.cpp b/src/amdinfer/bindings/python/core/inference_response.cpp index 53d70bb7..991c320a 100644 --- a/src/amdinfer/bindings/python/core/inference_response.cpp +++ b/src/amdinfer/bindings/python/core/inference_response.cpp @@ -30,6 +30,7 @@ #include // IWYU pragma: keep #include // for unordered_map +#include "amdinfer/bindings/python/core/bind_fp16.hpp" #include "amdinfer/bindings/python/helpers/docstrings.hpp" // for DOCS #include "amdinfer/bindings/python/helpers/keep_alive.hpp" // for keep_alive #include "amdinfer/bindings/python/helpers/print.hpp" // for toString From e71f7472831c5fc49406c94db3eb4bf95db537c4 Mon Sep 17 00:00:00 2001 From: Varun Sharma Date: Fri, 16 Jun 2023 10:22:16 -0700 Subject: [PATCH 2/2] Update changelog Signed-off-by: Varun Sharma --- CHANGELOG.rst | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/CHANGELOG.rst b/CHANGELOG.rst index 2ae97618..09c4c29c 100644 --- a/CHANGELOG.rst +++ b/CHANGELOG.rst @@ -33,12 +33,18 @@ Added * Custom memory storage classes in the memory pool (:pr:`166`) * C++ worker for executing C++ "models" (:pr:`172`) * Model chaining (:pr:`176`) and loading chains from ``modelLoad`` (:pr:`178`) +* vcpkg to resolve C++ dependencies (:pr:`188`) +* Tests with FP16 (:pr:`189` and :pr:`203`) +* Versioned models (:pr:`190`) +* Expand benchmarking with MLPerf app (:pr:`197`) and add to data to docs (:pr:`198`) + Changed ^^^^^^^ * Refactor how global state is managed (:pr:`125`) * Require the server as an argument for creating the NativeClient (:pr:`125`) +* Rename "RequestParameters" to "ParameterMap" (:pr:`125`) * Use a global memory pool to allocate memory for incoming requests (:pr:`149`) * Resolve the request at the incoming server rather than the batcher (:pr:`164`) * Add flags to run container-based tests in parallel (:pr:`168`) @@ -50,6 +56,8 @@ Changed * Location of test model lists moved to ``tests`` directory (:pr:`180`) * Close dynamically opened libraries (:pr:`186`) * Replace Jaeger exporter with OTLP (:pr:`187`) +* Change STRING type to BYTES and shape type from uint64 to int64 (:pr:`190`) +* Rename ONNX file to MXR correctly (:pr:`202`) Deprecated ^^^^^^^^^^ @@ -68,6 +76,8 @@ Fixed * Don't call ``next`` and ``prev`` on end iterators (:pr:`166`) * Use the right package name for ``g++`` in CentOS (:pr:`168`) * Fix building with different CMake options (:pr:`170`) +* Fix wheel generation with vcpkg (:pr:`191`) +* Load models at startup correctly (:pr:`195`) Security ^^^^^^^^