ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

Nano: add OS support table (#7429)

Browse source
This commit is contained in:
Yishuo Wang 2023-02-06 18:01:31 +08:00 committed by GitHub
parent 8911c69302
commit f4700422e1
3 changed files with 62 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
docs/readthedocs/source/_toc.yml
View file

@ -186,6 +186,8 @@ subtrees:
title: "Tips and Known Issues"
- file: doc/Nano/Overview/troubshooting
title: "Troubleshooting Guide"
- file: doc/Nano/Overview/support
title: "OS Support"
- file: doc/PythonAPI/Nano/index
title: "API Reference"

6
docs/readthedocs/source/doc/Nano/Overview/install.md
View file

@ -85,15 +85,15 @@ We support a wide range of PyTorch and Tensorflow. We only care the MAJOR.MINOR
Some specific note should be awared of when installing `bigdl-nano`.`
### Install on Linux
For Linux, Ubuntu (22.04/20.04/18.04) is recommended.
For Linux, Ubuntu (22.04/20.04) is recommended.
### Install on Windows
### Install on Windows (experimental support)
For Windows OS, users could only run `bigdl-nano-init` every time they open a new cmd terminal.
We recommend using Windows Subsystem for Linux 2 (WSL2) to run BigDL-Nano. Please refer to [Nano Windows install guide](../Howto/Install/windows_guide.md) for instructions.
### Install on MacOS
### Install on MacOS (experimental support)
#### MacOS with Intel Chip
Same usage as Linux, while some of the funcions now rely on lower version dependencies.

57
docs/readthedocs/source/doc/Nano/Overview/support.md Normal file
View file

@ -0,0 +1,57 @@
# BigDL-Nano Features
| Feature | Meaning |
| --------------------- | ----------------------------------------------------------------------- |
| **Intel-openmp** | Use Intel-openmp library to improve performance of multithread programs |
| **Jemalloc** | Use jemalloc as allocator |
| **Tcmalloc** | Use tcmalloc as allocator |
| **Neural-Compressor** | Neural-Compressor int8 quantization |
| **OpenVINO** | OpenVINO fp32/bf16/fp16/int8 acceleration on CPU/GPU/VPU |
| **ONNXRuntime** | ONNXRuntime fp32/int8 acceleration |
| **CUDA patch** | Run CUDA code even without GPU |
| **JIT** | PyTorch JIT optimization |
| **Channel last** | Channel last memory format |
| **BF16** | BFloat16 mixed precision training and inference |
| **IPEX** | Intel-extension-for-pytorch optimization |
| **Multi-instance** | Multi-process training and inference |
## Common Feature Support (Can be used in both PyTorch and TensorFlow)
| Feature | Ubuntu (20.04/22.04) | CentOS7 | MacOS (Intel chip) | MacOS (M-series chip) | Windows |
| --------------------- | -------------------- | ------- | ------------------ | --------------------- | ------- |
| **Intel-openmp** | ✅ | ✅ | ✅ | ② | ✅ |
| **Jemalloc** | ✅ | ✅ | ✅ | ❌ | ❌ |
| **Tcmalloc** | ✅ | ❌ | ❌ | ❌ | ❌ |
| **Neural-Compressor** | ✅ | ✅ | ❌ | ❌ | ? |
| **OpenVINO** | ✅ | ① | ❌ | ❌ | ? |
| **ONNXRuntime** | ✅ | ① | ✅ | ❌ | ? |
## PyTorch Feature Support
| Feature | Ubuntu (20.04/22.04) | CentOS7 | MacOS (Intel chip) | MacOS (M-series chip) | Windows |
| ------------------ | -------------------- | ------- | ------------------ | --------------------- | ------- |
| **CUDA patch** | ✅ | ✅ | ✅ | ? | ✅ |
| **JIT** | ✅ | ✅ | ✅ | ? | ✅ |
| **Channel last** | ✅ | ✅ | ✅ | ? | ✅ |
| **BF16** | ✅ | ✅ | ⭕ | ⭕ | ? |
| **IPEX** | ✅ | ✅ | ❌ | ❌ | ❌ |
| **Multi-instance** | ✅ | ✅ | ② | ② | ? |
## TensorFlow Feature Support
| Feature | Ubuntu (20.04/22.04) | CentOS7 | MacOS (Intel chip) | MacOS (M-series chip) | Windows |
| ------------------ | -------------------- | ------- | ------------------ | --------------------- | ------- |
| **BF16** | ✅ | ✅ | ⭕ | ⭕ | ? |
| **Multi-instance** | ③ | ③ | ②③ | ②③ | ? |
## Symbol Meaning
| Symbol | Meaning |
| ------ | -------------------------------------------------------------------------------------------------------- |
| ✅ | Supported |
| ❌ | Not supported |
| ⭕ | All Mac machines (Intel/M-series chip) do not support bf16 instruction set, so this feature is pointless |
| ① | This feature is only supported when used together with jemalloc |
| ② | This feature is supported but without any performance guarantee |
| ③ | Only Multi-instance training is supported for now |
| ? | Not tested |