Skip to content

Actions: NVIDIA/TensorRT-LLM

Actions

auto-assign

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
auto-assign.yml
1,682 workflow run results
1,682 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

wheel for tensorrt-llm auto-assign #1817: Issue #8819 labeled by kmnnmk212-source
1s
1s
[Feature]: AutoDeploy: investigate fp8 gemms that do not have pad to 16 requirement auto-assign #1816: Issue #8814 labeled by lucaslie
1s
1s
[Bug]: Output includes tokens from other prompts when host kv cache enabled auto-assign #1815: Issue #8813 labeled by pathorn
1s
1s
[Feature]: AutoDeploy: padding for fp8 linear kernel when size % 16 != 0 auto-assign #1814: Issue #8811 labeled by lucaslie
1s
1s
[Bug]: EXAONE-4.0-32B with VSWA causes OOM on A100-40G x 4 auto-assign #1813: Issue #8802 labeled by lkm2835
Skipped
Skipped
[Bug]: Can both enable_inductor and enable_piecewise_cuda_graph be set to true? auto-assign #1812: Issue #8784 labeled by morganliang-llm
1s
1s
[Performance]: [AutoDeploy] Benchmark Nemotron MoE FP8 ISL/OSL 8K/16K on H100, B200 auto-assign #1811: Issue #8782 labeled by galagam
14s
14s
[Bug][AutoDeploy] Execution hangs when enabling cudagraphs and AllReduceStrategy.AUTO auto-assign #1810: Issue #8781 labeled by suyoggupta
1s
1s
[Bug]: gpt-oss not run with error unsupported quant mode: [262144] auto-assign #1809: Issue #8730 labeled by karljang
Skipped
Skipped
When will Gemma 3 be supported? auto-assign #1808: Issue #3143 labeled by karljang
1s
1s
Add FP8 Support for Llama-4-Maverick on B200 (Feature Request) auto-assign #1807: Issue #4033 labeled by karljang
1s
1s
[Call for support] InternVL3 in Pytorch workflow auto-assign #1806: Issue #4225 labeled by karljang
1s
1s
Will there be support for the architecture 101? auto-assign #1805: Issue #5594 labeled by karljang
1s
1s
[Feature]: AutoDeploy: Allow for specifying mamba cache dtype auto-assign #1804: Issue #8763 labeled by suyoggupta
1s
1s
[Bug]: Segmentation fault on inference of batch of images auto-assign #1803: Issue #8651 labeled by karljang
1s
1s
[Bug]: Build and serving failures with Phi-3-mini-128k-instruct model FP8 quantization on B200 GPU with TensorRT-LLM auto-assign #1802: Issue #8308 labeled by karljang
1s
1s
TensorRT hangs auto-assign #1801: Issue #5665 labeled by karljang
1s
1s
Setting adaptive SamplingParams is not allowed when the model is loaded from the torch backend. auto-assign #1800: Issue #5780 labeled by karljang
1s
1s
[Eagle3] Accuracy Issue auto-assign #1799: Issue #5791 labeled by karljang
1s
1s
[Bug]: Can't run GPT-OSS models on DGX Spark auto-assign #1798: Issue #8474 labeled by karljang
1s
1s
[Feature]: AutoDeploy: skip post_clean_up logic for unused transforms to speed up transform pipeline auto-assign #1797: Issue #8742 labeled by lucaslie
1s
1s
[Usage]: Pytorch Workflow Add Multimodal Embedding into Qwen3 auto-assign #1796: Issue #7246 labeled by yechank-nvidia
1s
1s
[Bug]: MS Phi-4 Multimodal requires stop_words_list handling to prevent unnecessary token generation auto-assign #1795: Issue #7306 labeled by yechank-nvidia
2s
2s
[Feature]: Support for Qwen 3 VL auto-assign #1794: Issue #8722 labeled by yechank-nvidia
1s
1s
[AutoDeploy][Feature]: Basic LorA Support auto-assign #1793: Issue #8741 labeled by govind-ramnarayan
1s
1s