Merge pull request #47 from ROCm/multi_backend_readme_update

Update README for default branch change

Author: pnunna93

README.md

@@ -6,21 +6,26 @@ The `bitsandbytes` library is a lightweight Python wrapper around CUDA custom fu
 
 The library includes quantization primitives for 8-bit & 4-bit operations, through `bitsandbytes.nn.Linear8bitLt` and `bitsandbytes.nn.Linear4bit` and 8-bit optimizers through `bitsandbytes.optim` module.
 
-There are ongoing efforts to support further hardware backends, i.e. Intel CPU + GPU, AMD GPU, Apple Silicon. Windows support is quite far along and is on its way as well.
+This fork is actively developed for ROCm and updates are being pushed into `multi-backend-refactor` branch of upstream bitsandbytes. Users can use either of these to run bitsandbytes on AMD GPUs.
 
-**Please head to the official documentation page:**
+**Note: The default branch of this fork is switched from `rocm_enabled` to `rocm_enabled_multi_backend`. This is synced periodically with `multi-backend-refactor` branch of upstream, and latest developments are pushed here until upstream branch is merged into `main`.**
 
-**[https://huggingface.co/docs/bitsandbytes/main](https://huggingface.co/docs/bitsandbytes/main)**
-
-## ALPHA TESTERS WANTED: `multi-backend-refactor` AMD GPU + Intel CPU/GPU specific BNB backend implementations
+**Installation for ROCm:**
 
-We're in the process of a complex refactor in order to allow the support of additional hardware backends, other than CUDA, in BNB. The efforts around this are already quite far along and there's plenty of functionality already in place that is in need for users to take a hands-on approach! Mac support will likely soon also see progress. However, I recommend waiting 2 weeks until the device abstraction has further consolidated (**breaking changes upcoming**).
+For latest develop version:
+```bash
+git clone --recurse https://github.com/ROCm/bitsandbytes
+cd bitsandbytes
+git checkout rocm_enabled_multi_backend
+pip install -r requirements-dev.txt
+cmake -DCOMPUTE_BACKEND=hip -S . #Use -DBNB_ROCM_ARCH="gfx90a;gfx942" to target specific gpu arch
+make
+pip install .
+```
 
-Currently, you still need to compile from source, after checking out the `multi-backend-refactor` branch (instructions WIP, but [the current docs on the compilation from source](https://huggingface.co/docs/bitsandbytes/main/en/installation#compile-from-source) are a good starting point; [feel free to share tips / input in this Github discussion](https://github.com/TimDettmers/bitsandbytes/discussions/1219). We'll soon enable nightly releases to make this much easier for you!
+**For more details, please head to the official documentation page:**
 
-Please give feedback to us in [this dedicated Github Discussion space](https://github.com/TimDettmers/bitsandbytes/discussions/categories/catch-all-alpha-testing-the-multi-backend-refactor)!
-
-We're super excited about these recent developments and grateful for any constructive input or support that you can give to help us make this a reality. BNB is a community project and we're excited for your collaboration 🤗
+**[https://huggingface.co/docs/bitsandbytes/main](https://huggingface.co/docs/bitsandbytes/main)**
 
 ## License