Skip to content

Actions: pytorch/TensorRT

Actions

Issue Assigner

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
assigner.yml
913 workflow runs
913 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

✨[Feature] Refit Perf Study and Remove Weight Name Map Issue Assigner #4043: Issue #4140 labeled by cehongwang
13s
13s
🐛 [Bug] aten::index_put converter fails with "Dynamic shape in free dimensions is not supported" when a non-indexed dimension is dynamic Issue Assigner #4042: Issue #4139 labeled by narendasan
17s
17s
Preview branch that addresses a number of reported bugs Issue Assigner #4041: Pull request #4138 labeled by meta-cla bot
20s
20s
🐛 [Bug] Encountered bug when using Torch-TensorRT Issue Assigner #4040: Issue #4137 labeled by shahe-nv
15s
15s
fix: validator introduced in #4132 Issue Assigner #4039: Pull request #4136 labeled by meta-cla bot
15s
15s
🐛 [Bug] one ASR model can run with use_python_runtime=True while core dump on w/o it Issue Assigner #4038: Issue #4135 labeled by wenbingl
14s
14s
[WIP] Try meta's executorch Issue Assigner #4037: Pull request #4134 labeled by meta-cla bot
53s
53s
[WIP] Try meta's executorch Issue Assigner #4036: Pull request #4134 labeled by lanluo-nvidia
25s
25s
[WIP] Try meta's executorch Issue Assigner #4035: Pull request #4134 labeled by meta-cla bot
14s
14s
cherrypick: split index.Tensor converter for bool vs int indexing (#4123) Issue Assigner #4034: Pull request #4133 labeled by meta-cla bot
17s
17s
executorch Issue Assigner #4033: Pull request #4132 labeled by meta-cla bot
16s
16s
executorch Issue Assigner #4032: Pull request #4132 labeled by lanluo-nvidia
13s
13s
feat: support attn_bias for efficient SDPA Issue Assigner #4031: Pull request #4131 labeled by meta-cla bot
17s
17s
feat: Allow pulling the venv's torch after uv sync so that people don… Issue Assigner #4030: Pull request #4130 labeled by meta-cla bot
2m 15s
2m 15s
↔ [Converter] IAttention converter bypasses TRT native IAttention layer due to HuggingFace causal mask (attn_bias) Issue Assigner #4029: Issue #4129 labeled by chohk88
17s
17s
↔ [Converter] IAttention converter bypasses TRT native IAttention layer due to HuggingFace causal mask (attn_bias) Issue Assigner #4028: Issue #4129 labeled by chohk88
13s
13s
❓ [Question] Excessive GPU memory usage during constant folding pass causes OOM (Torch-TensorRT + Qwen-Image) Issue Assigner #4027: Issue #4128 labeled by Tongkaio
14s
14s
🐛 [Bug] Encountered bug when using Torch-TensorRT with CUDA-Graph Issue Assigner #4026: Issue #4126 labeled by wenbingl
14s
14s
cherry pick 4124 from main to 2.11 Issue Assigner #4025: Pull request #4125 labeled by meta-cla bot
2m 15s
2m 15s
handle symbolic shape for non tensor inputs in symbolic shape extraction Issue Assigner #4024: Pull request #4124 labeled by meta-cla bot
12s
12s
split index.Tensor converter for bool vs int indexing Issue Assigner #4023: Pull request #4123 labeled by meta-cla bot
16s
16s
only support cu130 for aarch64 Issue Assigner #4022: Pull request #4122 labeled by lanluo-nvidia
17s
17s
only support cu130 for aarch64 Issue Assigner #4021: Pull request #4122 labeled by meta-cla bot
21s
21s
Changed test_refit_cumsum test Issue Assigner #4020: Pull request #4121 labeled by meta-cla bot
16s
16s
fix: Fix the linting system to not constantly flag generated docs Issue Assigner #4019: Pull request #4120 labeled by meta-cla bot
14s
14s