Skip to content

Actions: NVIDIA/TensorRT

Actions

Remove feedback label on comment

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
feedback-update.yml
369 workflow runs
369 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Issue #4635: Use ml_dtypes to fix onnx_graphsurgeon import error Remove feedback label on comment #346: Issue comment #4653 (comment) created by yuanyao-nv
Skipped
Skipped
TensorRT just hangs when starting Remove feedback label on comment #345: Issue comment #4501 (comment) created by Muqi1029
1s
1s
Issue #4635: Use ml_dtypes to fix onnx_graphsurgeon import error Remove feedback label on comment #344: Issue comment #4653 (comment) created by onuralpszr
1s
1s
using QDQonnx export engine file,fp16and int8，speed is not faster than using ONNX withouout QDQ to export fp16 engine Remove feedback label on comment #343: Issue comment #4554 (comment) created by Floriangit12
1s
1s
onnx to engine failure of TensorRT 10.8.0 when running trtexec.exe on GPU 3060TI Remove feedback label on comment #341: Issue comment #4658 (comment) created by HaohuiHU
14s
14s
onnx to engine failure of TensorRT 10.8.0 when running trtexec.exe on GPU 3060TI Remove feedback label on comment #339: Issue comment #4658 (comment) created by HaohuiHU
12s
12s
Issue #4635: Use ml_dtypes to fix onnx_graphsurgeon import error Remove feedback label on comment #338: Issue comment #4653 (comment) created by onuralpszr
1s
1s
Could not find any implementation for node /network.0/network.0.0/norm1/LayerNormalization. Remove feedback label on comment #337: Issue comment #3610 (comment) created by JohnHerry
1s
1s
Cannot find op_type: "LayerNormalization" when convert the onnx model, using TensorRT 8.6 Remove feedback label on comment #336: Issue comment #2875 (comment) created by JohnHerry
1s
1s
Inconsistency between the outputs of dino onnx and dino trt engine Remove feedback label on comment #335: Issue comment #4404 (comment) created by ronghuaiyang
1s
1s
Conversion from onnx hurts accuracy when model is using fp16 Remove feedback label on comment #334: Issue comment #2922 (comment) created by JohnHerry
Skipped
Skipped
Tried to convert a mixed precision onnx model to TensorRT FP16 engine Remove feedback label on comment #333: Issue comment #4019 (comment) created by JohnHerry
1s
1s
configurePlugin is called repeatedly for my BF16 SDPA plugin — how to run initialization graph only once? Remove feedback label on comment #332: Issue comment #4654 (comment) created by poweiw
2s
2s
What is recommended way to convert into fp16 from fp32 Remove feedback label on comment #331: Issue comment #4656 (comment) created by JohnHerry
1s
1s
configurePlugin is called repeatedly for my BF16 SDPA plugin — how to run initialization graph only once? Remove feedback label on comment #330: Issue comment #4654 (comment) created by KarlDe1
13s
13s
configurePlugin is called repeatedly for my BF16 SDPA plugin — how to run initialization graph only once? Remove feedback label on comment #329: Issue comment #4654 (comment) created by poweiw
1s
1s
configurePlugin is called repeatedly for my BF16 SDPA plugin — how to run initialization graph only once? Remove feedback label on comment #328: Issue comment #4654 (comment) created by KarlDe1
12s
12s
configurePlugin is called repeatedly for my BF16 SDPA plugin — how to run initialization graph only once? Remove feedback label on comment #327: Issue comment #4654 (comment) created by KarlDe1
15s
15s
configurePlugin is called repeatedly for my BF16 SDPA plugin — how to run initialization graph only once? Remove feedback label on comment #326: Issue comment #4654 (comment) created by zhenhuaw-me
2s
2s
[Question] [TREx] Unexpected TREx Layer-Sum vs End-to-End Latency Behavior in LLM Generation Phase (Qwen2-VL on NVIDIA Thor) Remove feedback label on comment #325: Issue comment #4657 (comment) created by taoz27
10s
10s
Update goggles_action repository Remove feedback label on comment #324: Issue comment #4652 (comment) created by karljang
13s
13s
onnx_graphsurgeon incompatible with ONNX 1.20.0 Remove feedback label on comment #323: Issue comment #4635 (comment) created by hdnhan
1s
1s
Tritonserver serving Tensorrt model with cuda graph results in weird unconsistent outputs. Remove feedback label on comment #322: Issue comment #4651 (comment) created by WingEdge777
13s
13s
context->enqueue, enqueueV2, enqueueV3 Remove feedback label on comment #321: Issue comment #2872 (comment) created by Mirandatz
1s
1s
how to use polygraphy debug precision? Remove feedback label on comment #320: Issue comment #4616 (comment) created by JohnHerry
2s
2s