Skip to content

Actions: NVIDIA/TensorRT

Actions

Label New Issues

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
label_issue.yml
141 workflow runs
141 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

enable_context_fmha_fp32_acc Label New Issues #141: Issue #4674 opened by neezeeyee
14s
14s
Could not find any implementation for node {ForeignNode[3001...Add_1839]} Label New Issues #140: Issue #4673 opened by zzqiuzz
18s
18s
H100 receipts pack: M≪N work-shrink exact retrieval shows 308× lower J/query at N=20M (public-safe) Label New Issues #139: Issue #4672 opened by StanByriukov02
12s
12s
issue with TRT versioning Label New Issues #138: Issue #4671 opened by aakankshas-debug
15s
15s
Support lower fixed input resolution (e.g. 768×768) for Detectron2 Mask R‑CNN sample Label New Issues #137: Issue #4670 opened by luxi78
19s
19s
TensorRT: Quantization issues with convtranspose3D Label New Issues #136: Issue #4668 opened by Floriangit12
13s
13s
MTP weight loading failure of TensorRT-LLM 1.2.0rc5 when running GLM model on GPU NVIDIA B200 Label New Issues #135: Issue #4667 opened by Wirick
20s
20s
ONNX to TensorRT conversion fails due to GridSample Label New Issues #134: Issue #4666 opened by accessdenied35-rgb
21s
21s
TensorRT trying to gobble 100% GPU VRAM without considering what's already in use Label New Issues #133: Issue #4663 opened by Mashrien
16s
16s
Is there any why to make safe trt fp16 conversion according the torch AMP training process Label New Issues #132: Issue #4662 opened by JohnHerry
14s
14s
XXX failure of TensorRT X.Y when running XXX on GPU XXX Label New Issues #131: Issue #4661 opened by HaohuiHU
15s
15s
XXX failure of TensorRT X.Y when running XXX on GPU XXX Label New Issues #130: Issue #4660 opened by HaohuiHU
16s
16s
XXX failure of TensorRT X.Y when running XXX on GPU XXX Label New Issues #129: Issue #4659 opened by HaohuiHU
16s
16s
onnx to engine failure of TensorRT 10.8.0 when running trtexec.exe on GPU 3060TI Label New Issues #128: Issue #4658 opened by HaohuiHU
16s
16s
[Question] [TREx] Unexpected TREx Layer-Sum vs End-to-End Latency Behavior in LLM Generation Phase (Qwen2-VL on NVIDIA Thor) Label New Issues #127: Issue #4657 opened by taoz27
20s
20s
What is recommended way to convert into fp16 from fp32 Label New Issues #126: Issue #4656 opened by sarahliu-cisco
18s
18s
[TEST ISSUE] testing issue for CI Label New Issues #125: Issue #4655 opened by poweiw
16s
16s
configurePlugin is called repeatedly for my BF16 SDPA plugin — how to run initialization graph only once? Label New Issues #124: Issue #4654 opened by KarlDe1
13s
13s
Tritonserver serving Tensorrt model with cuda graph results in weird unconsistent outputs. Label New Issues #123: Issue #4651 opened by WingEdge777
9s
9s
TRT installation issue : Test post Label New Issues #122: Issue #4650 opened by aakankshas-debug
16s
16s
enqueueV3() return false, don't how to debug. i present my infer code Label New Issues #121: Issue #4649 opened by Kivw
14s
14s
TEST POST : PLS IGNORE Label New Issues #120: Issue #4648 opened by aakankshas-debug
10s
10s
ONNX and TensorRT output different Label New Issues #119: Issue #4647 opened by godbaz
13s
13s
GridSample outputs incorrect results in ONNX opset 20 (opset 18 works correctly) Label New Issues #118: Issue #4646 opened by Alcoholrithm
11s
11s
Precision/behavior failure of TensorRT 10.12 when running mixed FP32/FP16 image restoration on GPU RTX 3080 Laptop Label New Issues #117: Issue #4645 opened by rushdawn
13s
13s