Labels

• api-breaking

  api-breaking

  Accepted LLM API contract change that is backwards-incompatible

• api-compatible

  api-compatible

  Accepted LLM API contract change that is backwards-compatible

• AutoDeploy

  AutoDeploy

  <NV> AutoDeploy Backend

• AutoDeploy/Dashboard

  AutoDeploy/Dashboard

  <NV> AutoDeploy Backend: Dashboard related

• AutoDeploy/llmc-blocker

  AutoDeploy/llmc-blocker

  <NV> Tag for issues that are blocking AutoDeploy standalone repo

• breaking-api-change

  breaking-api-change

  When the PR breaks backwards compatibility

• bug

  bug

  Something isn't working

• Cherry-pick

  Cherry-pick

  It's a label that applies to Cherry-pick PR.

• ci improvement

  ci improvement

• Community Engagement

  Community Engagement

  help/insights needed from community

• Community want to contribute

  Community want to contribute

  PRs initiated from Community

• CUDA Graph

  CUDA Graph

• Customized kernels

  Customized kernels

  <NV>Specialized/modified CUDA kernels in TRTLLM for LLM ops, beyond standard TRT. Dev & perf.

• Decoding/Sampling

  Decoding/Sampling

  <NV>Token sampling algorithms in TRTLLM for text gen (top-k, top-p, beam).

• deepseek-v4

  deepseek-v4

• dependencies

  dependencies

  Pull requests that update a dependency file

• Disaggregated serving

  Disaggregated serving

  <NV>Deploying with separated, distributed components (params, kv-cache, compute). Arch & perf.

• Doc

  Doc

  <NV>TRTLLM's textual/illustrative materials: API refs, guides, tutorials. Improvement & clarity.

• duplicate

  duplicate

  This issue or pull request already exists

• Ease of Use

  Ease of Use

  Items about improving or complaints about TRTLLM ease of use

• feature request

  feature request

  New feature or request. This includes new model, dtype, functionality support

• Frontend

  Frontend

  <NV>Frontend of the LLM workflow

• functionality issue

  functionality issue

• gagam-slack-watch

  gagam-slack-watch

  Label for getting slack notifications via GitHub Slack app

• General perf

  General perf

  <NV>Broad performance issues not specific to a particular component

• help wanted

  help wanted

  Extra attention is needed

• Inference runtime

  Inference runtime

  <NV>General operational aspects of TRTLLM execution not in other categories.

• Infra

  Infra

  <NV>automated tests, build checks, github actions, system stability & efficiency.

• Installation

  Installation

  Setting up and building TRTLLM: compilation, pip install, dependencies, env config, CMake.

• Investigating

  Investigating