Labels

• blocked

  This is blocked from being supported
• bug

  Something isn't working
• build

  Issues pertaining to builds
• C API

  Relating to Triton Inference Server's C APIs
• cherry-pick
• crash

  Related to server crashes, segfaults, etc.
• documentation issue

  Documentation isn't correct or could be improved
• duplicate

  This issue or pull request already exists
• enhancement

  New feature or request
• good first issue

  Good for newcomers
• grpc

  Related to the GRPC server
• help wanted

  Extra attention is needed
• invalid

  This doesn't seem right
• investigating

  The developement team is investigating this issue
• kubernetes
• memory

  Related to memory usage, memory growth, and memory leaks
• metrics

  Related to deployment, inference, GPU metrics (prometheus, grafana, dcgm, etc.)
• models: fix

  Map models related fixes
• module: backends

  Issues related to the backends
• module: clients

  Issues related to Perf Analyzer and clients
• module: frontends

  Issues related to the triton frontends
• module: platforms

  Issues related to platforms, hardware, and support matrix
• module: server

  Issues related to the server core
• onnx

  Related to ONNX or ONNXRuntime
• openai

  OpenAI related
• performance

  A possible performance tune-up
• PR: build

  Changes that affect the build system or external dependencies
• PR: ci

  Changes to our CI configuration files and scripts
• PR: docs

  Documentation only changes
• PR: feat

  A new feature