experiments
/
STT
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Update supported architectures doc

This commit is contained in:
Reuben Morais 2021-07-29 16:34:49 +02:00
parent c69735e3b6
commit d119957586
1 changed files with 10 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
doc/SUPPORTED_PLATFORMS.rst
View File

@ -7,65 +7,46 @@ Here we maintain the list of supported platforms for deployment.
*Note that 🐸STT currently only provides packages for CPU deployment with Python 3.5 or higher on Linux. We're working to get the rest of our usually supported packages back up and running as soon as possible.* *Note that 🐸STT currently only provides packages for CPU deployment with Python 3.5 or higher on Linux. We're working to get the rest of our usually supported packages back up and running as soon as possible.*
Linux / AMD64 without GPU Linux / AMD64
^^^^^^^^^^^^^^^^^^^^^^^^^ ^^^^^^^^^^^^^^^^^^^^^^^^^
* x86-64 CPU with AVX/FMA (one can rebuild without AVX/FMA, but it might slow down performance) * x86-64 CPU with AVX/FMA (one can rebuild without AVX/FMA, but it might slow down performance)
* Ubuntu 14.04+ (glibc >= 2.19, libstdc++6 >= 4.8) * glibc >= 2.24, libstdc++6 >= 6.3
* Full TensorFlow runtime (``stt`` packages) * TensorFlow Lite runtime
* TensorFlow Lite runtime (``stt-tflite`` packages)
Linux / AMD64 with GPU
^^^^^^^^^^^^^^^^^^^^^^
* x86-64 CPU with AVX/FMA (one can rebuild without AVX/FMA, but it might slow down performance)
* Ubuntu 14.04+ (glibc >= 2.19, libstdc++6 >= 4.8)
* CUDA 10.0 (and capable GPU)
* Full TensorFlow runtime (``stt`` packages)
* TensorFlow Lite runtime (``stt-tflite`` packages)
Linux / ARMv7 Linux / ARMv7
^^^^^^^^^^^^^ ^^^^^^^^^^^^^
* Cortex-A53 compatible ARMv7 SoC with Neon support * Cortex-A53 compatible ARMv7 SoC with Neon support
* Raspbian Buster-compatible distribution * Raspbian Buster-compatible distribution
* TensorFlow Lite runtime (``stt-tflite`` packages) * TensorFlow Lite runtime
Linux / Aarch64 Linux / Aarch64
^^^^^^^^^^^^^^^ ^^^^^^^^^^^^^^^
* Cortex-A72 compatible Aarch64 SoC * Cortex-A72 compatible Aarch64 SoC
* ARMbian Buster-compatible distribution * ARMbian Buster-compatible distribution
* TensorFlow Lite runtime (``stt-tflite`` packages) * TensorFlow Lite runtime
Android / ARMv7 Android / ARMv7
^^^^^^^^^^^^^^^ ^^^^^^^^^^^^^^^
* ARMv7 SoC with Neon support * ARMv7 SoC with Neon support
* Android 7.0-10.0 * Android 7.0-10.0
* NDK API level >= 21 * NDK API level >= 21
* TensorFlow Lite runtime (``stt-tflite`` packages) * TensorFlow Lite runtime
Android / Aarch64 Android / Aarch64
^^^^^^^^^^^^^^^^^ ^^^^^^^^^^^^^^^^^
* Aarch64 SoC * Aarch64 SoC
* Android 7.0-10.0 * Android 7.0-10.0
* NDK API level >= 21 * NDK API level >= 21
* TensorFlow Lite runtime (``stt-tflite`` packages) * TensorFlow Lite runtime
macOS / AMD64 macOS / AMD64
^^^^^^^^^^^^^ ^^^^^^^^^^^^^
* x86-64 CPU with AVX/FMA (one can rebuild without AVX/FMA, but it might slow down performance) * x86-64 CPU with AVX/FMA (one can rebuild without AVX/FMA, but it might slow down performance)
* macOS >= 10.10 * macOS >= 10.10
* Full TensorFlow runtime (``stt`` packages) * TensorFlow Lite runtime
* TensorFlow Lite runtime (``stt-tflite`` packages)
Windows / AMD64 without GPU Windows / AMD64
^^^^^^^^^^^^^^^^^^^^^^^^^^^ ^^^^^^^^^^^^^^^^^^^^^^^^^^^
* x86-64 CPU with AVX/FMA (one can rebuild without AVX/FMA, but it might slow down performance) * x86-64 CPU with AVX/FMA (one can rebuild without AVX/FMA, but it might slow down performance)
* Windows Server >= 2012 R2 ; Windows >= 8.1 * Windows Server >= 2012 R2 ; Windows >= 8.1
* Full TensorFlow runtime (``stt`` packages) * TensorFlow Lite runtime
* TensorFlow Lite runtime (``stt-tflite`` packages)
Windows / AMD64 with GPU
^^^^^^^^^^^^^^^^^^^^^^^^
* x86-64 CPU with AVX/FMA (one can rebuild without AVX/FMA, but it might slow down performance)
* Windows Server >= 2012 R2 ; Windows >= 8.1
* CUDA 10.0 (and capable GPU)
* Full TensorFlow runtime (``stt`` packages)
* TensorFlow Lite runtime (``stt-tflite`` packages)