Skip to content

Actions: NVIDIA/TensorRT-LLM

Actions

auto-assign

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
auto-assign.yml
1,908 workflow run results
1,908 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[Feature]: AutoDeploy: use torch's built-in rms norm as reference auto-assign #2022: Issue #9526 labeled by lucaslie
1s
1s
[Feature]: AutoDeploy: l2-norm pattern matching infra auto-assign #2021: Issue #9525 labeled by lucaslie
1s
1s
Support for q4_0 format - google/gemma-3-27b-it-qat-q4_0-unquantized auto-assign #2020: Issue #9523 labeled by albertnanda
1s
1s
[Bug]: Should we add boudary check in write value to smemFinal in indexer_topk? auto-assign #2019: Issue #9519 labeled by MARD1NO
1s
1s
How can I use gen_cubins.py in the XQA directory to compile a cubin for SM101? auto-assign #2018: Issue #9517 labeled by july2n
1s
1s
[Bug]: Managed Weights fail with NVFP4: Strict Type Check & Incorrect Allocation in v1.2.0rc4 auto-assign #2017: Issue #9503 labeled by JohnTDI-cpu
1s
1s
[Feature]: Remove the autotuner invocation from AD's nvfp4_gemm operator auto-assign #2016: Issue #9496 labeled by nzmora-nvidia
1s
1s
[Feature]: Remove the autotuner invocation from AD's nvfp4_gemm operator auto-assign #2015: Issue #9496 labeled by nzmora-nvidia
1s
1s
[Usage]: [Question] Differences between trtllm-build and trtllm-bench --build auto-assign #2014: Issue #9334 labeled by pcastonguay
1s
1s
[Feature]: Detailed Usage Guide for AFD Support in TensorRT-LLM auto-assign #2013: Issue #9489 labeled by Alan-D-Chen
1s
1s
[Bug]: 【trtllm-serve】Unexpected TTFT Behavior: Longer Input Shows Lower Time-to-First-Token auto-assign #2012: Issue #9470 labeled by kurosakiharachan
1s
1s
[Feature]: huggingface revision (aka tag) for serve command auto-assign #2011: Issue #9463 labeled by oplatek
5s
5s
[Feature]: AutoDeploy: spec dec TP > 1 tests auto-assign #2010: Issue #9417 labeled by pcastonguay
1s
1s
[Feature]: AutoDeploy: Fully-fledged GPT-OSS support auto-assign #2009: Issue #9460 labeled by Fridah-nv
1s
1s
[Feature]: AutoDeploy: Fully-fledged GPT-OSS support auto-assign #2008: Issue #9460 labeled by Fridah-nv
1s
1s
[AutoDeploy[bug-9379] Fixing sharding-related bug. auto-assign #2007: Issue #9451 labeled by greg-kwasniewski1
1s
1s
[Bug]: Repetition, Frequency, and Presence Penalty Not Applied in TensorRT-LLM Completions API auto-assign #2006: Issue #9442 labeled by akakakakakaa
1s
1s
[Bug]: Assertion failed: Can't remove link from block auto-assign #2005: Issue #9436 labeled by wjueyao
1s
1s
[Bug]: NameError in memory profiler on Jetson device. auto-assign #2004: Issue #9432 labeled by bonginn
1s
1s
[AutoDeploy][Feature] Overlap scheduling + speculative decoding in AutoDeploy auto-assign #2003: Issue #9421 labeled by govind-ramnarayan
1s
1s
[Feature]: Are there plans support qwen3-vl in TensorRT backend? auto-assign #2002: Issue #9418 labeled by july8023
Skipped
Skipped
[Feature]: AutoDeploy: spec dec TP > 1 tests auto-assign #2001: Issue #9417 labeled by lucaslie
1s
1s
[Feature]: AutoDeploy: nano 3 custom modeling code follow-ups auto-assign #2000: Issue #9413 labeled by lucaslie
1s
1s
[Bug]: Requests to trtllm-serve serve are executed sequentially if max_tokens is not provided auto-assign #1999: Issue #9412 labeled by Jensonah1
1s
1s
[New Model]: Add Support for T5Gemma Architecture auto-assign #1998: Issue #9399 labeled by pcastonguay
Skipped
Skipped