IREE Python Runtime Components
Project description
IREE Python Runtime Components
This package provides an API for running compiled IREE binaries and interfacing with the hardware-abstraction-layer.
Tracing
Execution of calls against binaries can be traced for later replay (i.e. via
tools like iree-run-module
). This can be set up either explicitly or
via environment variables.
To trace via environment variable, set IREE_SAVE_CALLS
to a directory to dump
traces into. Each created SystemContext
will result in one calls.yaml
file (with an index appended to the stem for multiples). Any referenced
module binaries will be dumped into the same directory and referenced by the
YAML file.
Explicit API
tracer = iree.runtime.Tracer(some_dir)
config = iree.runtime.Config(driver, tracer)
...
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distributions
Built Distributions
File details
Details for the file iree_runtime_instrumented-20230524.529-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
.
File metadata
- Download URL: iree_runtime_instrumented-20230524.529-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
- Upload date:
- Size: 3.7 MB
- Tags: CPython 3.11, manylinux: glibc 2.17+ x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.11.2
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 4b58b568fde61a2a34e8254b3d99a136cc397378e71fdbd67a1c766bf2f3556d |
|
MD5 | 832507fbfa9b63e66fc7aeadbbab22d0 |
|
BLAKE2b-256 | 164eb06f5ad0e945dc2cb1c38e4a9acd2d05f095a13b5d38a3b61c115ae6ade5 |
File details
Details for the file iree_runtime_instrumented-20230524.529-cp311-cp311-macosx_11_0_universal2.whl
.
File metadata
- Download URL: iree_runtime_instrumented-20230524.529-cp311-cp311-macosx_11_0_universal2.whl
- Upload date:
- Size: 2.4 MB
- Tags: CPython 3.11, macOS 11.0+ universal2 (ARM64, x86-64)
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.11.2
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | b97574e5203bcc6ca73304ed2c866096378147f434e3a4403effd38cdd0c5d90 |
|
MD5 | 6e312393802c6fc2d7a9b27a44ff6f4a |
|
BLAKE2b-256 | 77917957692ac29a8b3fa492de9e0222383bb12d1cb47ebdb3e5d0a54d0a9de0 |
File details
Details for the file iree_runtime_instrumented-20230524.529-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
.
File metadata
- Download URL: iree_runtime_instrumented-20230524.529-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
- Upload date:
- Size: 3.7 MB
- Tags: CPython 3.10, manylinux: glibc 2.17+ x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.11.2
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | aae0718aa037eb5a66417870aa6b37df98e16fa7a8958ac8fc89eeb53455973a |
|
MD5 | 32e1450b1c700ca192502de2c049bf93 |
|
BLAKE2b-256 | 883817392b81b6c5aadfa727588c9490b9c7c76ec91c73dc1dc6f349c3e95555 |
File details
Details for the file iree_runtime_instrumented-20230524.529-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
.
File metadata
- Download URL: iree_runtime_instrumented-20230524.529-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
- Upload date:
- Size: 3.7 MB
- Tags: CPython 3.9, manylinux: glibc 2.17+ x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.11.2
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 6256cb3335a6aa224779e58381910fd13c1134496804e9cf0b48c5dbb08a3617 |
|
MD5 | 47cd5e4d623eb4bdc23501b814eecaa1 |
|
BLAKE2b-256 | b5a14d7ee259cc20e04279a78640791535e6ba356ed4c69075f14a9be0cd4e3e |
File details
Details for the file iree_runtime_instrumented-20230524.529-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
.
File metadata
- Download URL: iree_runtime_instrumented-20230524.529-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
- Upload date:
- Size: 3.7 MB
- Tags: CPython 3.8, manylinux: glibc 2.17+ x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.11.2
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 13abd53ff84e63d50df0d6ecee789f6a0e3d6e4bfe7bf3fc5ffee47a5f6039e3 |
|
MD5 | c5464ab3b6ea74c459f7cf06cd4aa7fd |
|
BLAKE2b-256 | f6a47f28fa2b3387a692de9e4a34989e3a5283c26c4535488e6446fb81a60f35 |