issues
search
triton-inference-server
/
onnxruntime_backend
The Triton backend for the ONNX Runtime.
BSD 3-Clause "New" or "Revised" License
125
stars
54
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Set CMake version to 3.27.7 (#222)
#223
mc-nv
closed
10 months ago
0
Set CMake version to 3.27.7
#222
mc-nv
closed
10 months ago
0
Add ORT patch build (#218)
#221
mc-nv
closed
10 months ago
0
Model failed to create because of output dimensions
#220
nyanmn
opened
10 months ago
0
Use compliant preprocessor on windows
#219
tanmayv25
closed
10 months ago
0
Add ORT patch build
#218
Tabrizian
closed
10 months ago
0
Support arbitrary options for execution providers
#217
gedoensmax
opened
10 months ago
0
Fix input check for initializer input (#215)
#216
jbkyang-nvi
closed
11 months ago
0
Fix input check for initializer input
#215
GuanLuo
closed
11 months ago
0
Update build instructions to support ORT 1.16.0 (#212)
#214
mc-nv
closed
1 year ago
0
Add scalar support in ORT backend
#213
Tabrizian
closed
1 year ago
0
Update build instructions to support ORT 1.16.0
#212
mc-nv
closed
1 year ago
0
Openvino doesn't work, it degrades inference performance instead
#211
SunnyGhj
closed
1 year ago
4
Error while Loading YOLOv8 Model with EfficientNMS_TRT Plugin in TRITON
#210
whitewalker11
opened
1 year ago
2
Remove support for Maxwell architecture from the backend build
#209
mc-nv
closed
1 year ago
0
Enable parallel instance loading backend attribute
#208
rmccorm4
closed
1 year ago
0
how to use onnxruntime profiling in triton
#207
cyh-ustc
opened
1 year ago
0
Include libtbb.so (#204)
#206
kthui
closed
1 year ago
0
Include libtbb.so (#204)
#205
kthui
closed
1 year ago
0
Include libtbb.so
#204
kthui
closed
1 year ago
0
Onnxruntime backend error when workload is high since Triton uses CUDA 12
#203
zeruniverse
opened
1 year ago
4
Fix the memory type of output tensor when warm-up is enabled
#202
krishung5
closed
1 year ago
1
Dyas test
#201
dyastremsky
closed
1 year ago
0
OpenVINO 2023.0.0
#200
kthui
closed
1 year ago
0
Add GitHub action to format and lint code
#199
dyastremsky
closed
1 year ago
1
Auto-formatting
#197
dyastremsky
closed
1 year ago
0
Update README.md with custom ops usage example
#196
msyulia
closed
1 year ago
2
Add option to set ORT_DISABLE_ALL as optimization
#195
casassg
closed
9 months ago
7
GPU memory leak with high load for ONNX model
#198
junwang-wish
opened
1 year ago
3
Add `enable_dynamic_shapes` To Model Config To Resolve CNN Memory Leaks With OpenVino EP
#194
narolski
opened
1 year ago
0
Update `main` post-23.05 release
#193
mc-nv
closed
1 year ago
0
How to create onnx model for ragged batching?
#192
Sitcebelly
opened
1 year ago
0
InvalidArgumentError: The tensor Input (Input) of Slice op is not initialized.
#191
qiu-pinggaizi
opened
1 year ago
0
Include compute_90 architecture build on Jetson
#190
dyastremsky
closed
1 year ago
2
Cherry pick multi-GPU fix to ORT 1.15.0
#189
GuanLuo
closed
1 year ago
1
Changes to support 23.05
#188
mc-nv
closed
1 year ago
0
adding WAR for installing openvino 2022.1 on ubuntu22.04
#187
nnshah1
closed
1 year ago
0
Implement per-model memory usage reporting
#186
GuanLuo
closed
1 year ago
0
Fatal error: TRT:EfficientNMS_TRT(-1) is not a registered function/op
#185
levipereira
opened
1 year ago
2
Update README and versions for 23.04 branch
#184
mc-nv
closed
1 year ago
0
Remove the cherry-pick fix
#183
tanmayv25
closed
1 year ago
0
Onnxruntime Error
#182
courage622
closed
1 year ago
0
Support initializer as inference request input. Add test (#180)
#181
tanmayv25
closed
1 year ago
0
Support initializer as inference request input. Add test
#180
GuanLuo
closed
1 year ago
0
Add flags to allow platform-specific build
#179
dyastremsky
closed
1 year ago
1
Update post-23.03 release
#178
mc-nv
closed
1 year ago
0
Support initializer as inference request input - onnxruntime backend
#177
taoisu
closed
1 year ago
7
Add codeql static analysis
#176
dyastremsky
closed
1 year ago
1
Can I build the Onnxruntime backend for Windows without Docker??
#175
victorsoyvictor
opened
1 year ago
0
Serialize ModelInstanceState constructor for parallel model loading
#174
kthui
closed
1 year ago
0
Previous
Next