Logo
Poplar Triton Backend: User Guide
Version: latest
  • 1. Introduction
    • 1.1. Overview
    • 1.2. Setting the environment variables
    • 1.3. Building the Triton server
    • 1.4. Configuring the model repository
      • 1.4.1. PopEF files
      • 1.4.2. Input / output name mapping
      • 1.4.3. Triton model configuration
        • Backend
        • Instance groups
        • Batching
        • Timeouts
        • Synchronous execution
    • 1.5. Configuring the Poplar backend
    • 1.6. Starting the server
    • 1.7. Profiling
      • 1.7.1. Triton performance analyzer and metrics
    • 1.8. Limitations
  • 2. API reference
    • 2.1. BackendState
    • 2.2. ModelState
    • 2.3. InputBuffers
    • 2.4. OutputBuffers
    • 2.5. ModelInstanceState
    • 2.6. RequestCollection
    • 2.7. Request
    • 2.8. Tracepoint
    • 2.9. Latch
  • 3. Trademarks & copyright
Poplar Triton Backend: User Guide

Search help

Note: Searching from the top-level index page will search all documents. Searching from a specific document will search only that document.

  • Find an exact phrase: Wrap your search phrase in "" (double quotes) to only get results where the phrase is exactly matched. For example "PyTorch for the IPU" or "replicated tensor sharding"
  • Prefix query: Add an * (asterisk) at the end of any word to indicate a prefix query. This will return results containing all words with the specific prefix. For example tensor*
  • Fuzzy search: Use ~N (tilde followed by a number) at the end of any word for a fuzzy search. This will return results that are similar to the search word. N specifies the “edit distance” (fuzziness) of the match. For example Polibs~1
  • Words close to each other: ~N (tilde followed by a number) after a phrase (in quotes) returns results where the words are close to each other. N is the maximum number of positions allowed between matching words. For example "ipu version"~2
  • Logical operators. You can use the following logical operators in a search:
    • + signifies AND operation
    • | signifies OR operation
    • - negates a single word or phrase (returns results without that word or phrase)
    • () controls operator precedence

Poplar Triton Backend: User Guide

  • 1. Introduction
    • 1.1. Overview
    • 1.2. Setting the environment variables
    • 1.3. Building the Triton server
    • 1.4. Configuring the model repository
      • 1.4.1. PopEF files
      • 1.4.2. Input / output name mapping
      • 1.4.3. Triton model configuration
        • Backend
        • Instance groups
        • Batching
        • Timeouts
        • Synchronous execution
    • 1.5. Configuring the Poplar backend
    • 1.6. Starting the server
    • 1.7. Profiling
      • 1.7.1. Triton performance analyzer and metrics
    • 1.8. Limitations
  • 2. API reference
    • 2.1. BackendState
    • 2.2. ModelState
    • 2.3. InputBuffers
    • 2.4. OutputBuffers
    • 2.5. ModelInstanceState
    • 2.6. RequestCollection
    • 2.7. Request
    • 2.8. Tracepoint
    • 2.9. Latch
  • 3. Trademarks & copyright
Next

Revision 8f912932.