Logo
Model Runtime: User Guide
Version: latest
  • 1. Introduction
  • 2. Model Runtime overview
    • 2.1. Finding hardware
    • 2.2. Data transfers
    • 2.3. Executable upload
    • 2.4. Tensor data
    • 2.5. Managing data sources and targets
    • 2.6. Queues of data
    • 2.7. Buffers
  • 3. Using ModelRunner
    • 3.1. Execution modes
    • 3.2. Replication
    • 3.3. Multithreading
    • 3.4. Frozen inputs
    • 3.5. Conditional execution
    • 3.6. Dynamic batch sizing
    • 3.7. Improved model fusion and I/O overlap performance
    • 3.8. Monitoring statistics
  • 4. Sessions
    • 4.1. Creating a session
      • 4.1.1. Session configuration options
      • 4.1.2. Session predicates
    • 4.2. Uploading your model to the IPU
    • 4.3. Handlers for model tensors
    • 4.4. Running programs
    • 4.5. Retrieving information from a session
    • 4.6. Managing queues of tensor data
    • 4.7. Verification
  • 5. Managing devices
    • 5.1. Device
    • 5.2. Device manager
      • 5.2.1. Control which devices to use
  • 6. Queue manager
  • 7. Error handling
  • 8. Tools
    • 8.1. Callbacks benchmark
    • 8.2. Queues benchmark
    • 8.3. Real data
  • 9. Logging
  • 10. C++ API reference
    • 10.1. High-level API
      • 10.1.1. Device management
      • 10.1.2. Tensor memory representation
      • 10.1.3. ModelRunner
    • 10.2. Low-level API
      • 10.2.1. Anchor callback management
      • 10.2.2. Queue memory management
      • 10.2.3. Queue management
      • 10.2.4. Runtime management
  • 11. Python API reference
    • 11.1. High-level API
      • 11.1.1. Device management
      • 11.1.2. Tensor memory representation
      • 11.1.3. ModelRunner
    • 11.2. Low-level API
      • 11.2.1. Anchor callback management
      • 11.2.2. Queue management
      • 11.2.3. Runtime management
  • 12. Legal notices
  • A. Examples
    • A.1. General examples
      • A.1.1. ModelRunner examples (high-level API)
      • A.1.2. Session examples (low-level API)
    • A.2. Helper functions used by the examples
    • A.3. Generating an example PopEF file
Model Runtime: 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

Revision 50c345f0.