Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fix FP16 binding #208

Merged
merged 2 commits into from
Jun 16, 2023
Merged

Fix FP16 binding #208

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7d40605
Add bind header
varunsh-xilinx Jun 16, 2023
e71f747
Update changelog
varunsh-xilinx Jun 16, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 10 additions & 0 deletions CHANGELOG.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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`)
Expand All @@ -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
^^^^^^^^^^
Expand All @@ -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
^^^^^^^^
Expand Down
1 change: 1 addition & 0 deletions src/amdinfer/bindings/python/core/inference_response.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,7 @@
#include <sstream> // IWYU pragma: keep
#include <unordered_map> // 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
Expand Down