-
Notifications
You must be signed in to change notification settings - Fork 2.7k
All issues
Issue creation is restricted in this repository
- #15044 · laikhtewari opened
on Jun 6, 2026 1 - #3148 · juney-nvidia opened
on Mar 29, 2025 5 - #3124 · juney-nvidia opened
on Mar 27, 2025 11
Issues
is:issue state:open
is:issue state:open
Search results
[Bug]: MAX_UTILIZATION resume raises
RequestError: 'modality_type'for Nemotron Nano 3 OmnibugSomething isn't workingSomething isn't workingLLM API<NV>High-level LLM Python API & tools (e.g., trtllm-llmapi-launch) for TRTLLM inference/workflows.<NV>High-level LLM Python API & tools (e.g., trtllm-llmapi-launch) for TRTLLM inference/workflows.MultimodalLabel for issues & PRs regarding Multimodal related objectsLabel for issues & PRs regarding Multimodal related objectsStatus: Open.#17882 In NVIDIA/TensorRT-LLM;[Feature]: Router Replay(R3): capture per-token MoE routing for train/inference alignment
feature requestNew feature or request. This includes new model, dtype, functionality supportNew feature or request. This includes new model, dtype, functionality supportStatus: Open.#17778 In NVIDIA/TensorRT-LLM;[Bug]: etcd cluster storage loses stored empty-string values
Infra<NV>automated tests, build checks, github actions, system stability & efficiency.<NV>automated tests, build checks, github actions, system stability & efficiency.Status: Open.#17765 In NVIDIA/TensorRT-LLM;[Bug]: etcd cluster storage delete drops its success result
Customized kernels<NV>Specialized/modified CUDA kernels in TRTLLM for LLM ops, beyond standard TRT. Dev & perf.<NV>Specialized/modified CUDA kernels in TRTLLM for LLM ops, beyond standard TRT. Dev & perf.Status: Open.#17764 In NVIDIA/TensorRT-LLM;[Bug]: HTTP cluster get_prefix exposes expired keys before cleanup sweep
Disaggregated serving<NV>Deploying with separated, distributed components (params, kv-cache, compute). Arch & perf.<NV>Deploying with separated, distributed components (params, kv-cache, compute). Arch & perf.Status: Open.#17763 In NVIDIA/TensorRT-LLM;[Bug]: WatchEventQueue.drain leaves unfinished queue tasks
Testing<NV>Continuous integration, build system, and testing infrastructure issues<NV>Continuous integration, build system, and testing infrastructure issuesStatus: Open.#17762 In NVIDIA/TensorRT-LLM;[Bug]: HTTP cluster storage returns 400 for valid empty results
Infra<NV>automated tests, build checks, github actions, system stability & efficiency.<NV>automated tests, build checks, github actions, system stability & efficiency.Status: Open.#17761 In NVIDIA/TensorRT-LLM;[Bug]: skill naming checker crashes on malformed YAML frontmatter
Testing<NV>Continuous integration, build system, and testing infrastructure issues<NV>Continuous integration, build system, and testing infrastructure issuesStatus: Open.#17759 In NVIDIA/TensorRT-LLM;[Bug]: telemetry schema drift checker ignores required-field drift
Testing<NV>Continuous integration, build system, and testing infrastructure issues<NV>Continuous integration, build system, and testing infrastructure issuesStatus: Open.#17757 In NVIDIA/TensorRT-LLM;[Bug]: model registry validator accepts padded names and config IDs
AutoDeploy<NV> AutoDeploy Backend<NV> AutoDeploy BackendStatus: Open.#17755 In NVIDIA/TensorRT-LLM;[Bug]: AutoDeploy import checker silently passes unreadable source files
AutoDeploy<NV> AutoDeploy Backend<NV> AutoDeploy BackendStatus: Open.#17753 In NVIDIA/TensorRT-LLM;[Bug]: ruff-legacy pre-commit hook reports all baseline violations as regressions on Windows
Windows<NV>Windows operating system specific issues and compatibility problems<NV>Windows operating system specific issues and compatibility problemsStatus: Open.#17743 In NVIDIA/TensorRT-LLM;