This commit adds a Dockerfile that sets up the environment for Petals, as well as a GitHub Action to build the corresponding image on each push to the main branch.
Fixes:
- An exception while creating a model with `ptune/deep_ptune` and `low_cpu_mem_usage=True` (which is currently default).
- dtype mismatch between the prompts and the rest of the model in `.forward()`.
Currently, the schemas use `torch.float32`, so all inputs and outputs converted to float32 before sending and after receiving on both servers and clients. This creates a huge slowdown for the system.
* This PR makes the schemas use the server's `--torch_dtype` argument (default is `torch.bloat16` for BLOOM-176B)
* an option for client to request a specific output compression. Use case 1: client sends quantized inputs and expects quantized inputs in return. Use case 2: client uses quantization for gradients w.r.t. activations, but keeps grads w.r.t. __prompts__ as is for greater precision.
* a comment explaining the purpose of NoSpendingPolicy - since we likely won't have it for the workshop
* a test with custom compression (janky implementation for testing purposes)
Co-authored-by: justheuristic <justheuristic@gmail.com>
1. Petals can be now installed using `pip install git+https://github.com/bigscience-workshop/petals`
- In case if you already cloned the repo, you can do `pip install .` or `pip install .[dev]`
2. Moved `src` => `src/petals`
- Replaced `from src.smth import smth` with `from petals.smth import smth`
3. Moved `cli` => `src/petals/cli`
- Replaced `python -m cli.run_smth` with `python -m petals.cli.run_smth` (all utilities are now available right after pip installation)
4. Moved the `requirements*.txt` contents to `setup.cfg` (`requirements.txt` for packages is not supported well by modern packaging utils)
5. Increased the package version from `0.2` to `1.0alpha1`
This PR:
1. Makes inference/forward/backward calls on client remember the dtype and device of source tensors, then move/cast the outputs to the same dtype/device. This way:
- Users don't need to make changes in the code launching `RemoteSequential` to make it run on a different device.
- `model.generate()` also starts to support both CPU and GPU.
2. Sets default `low_cpu_mem_usage=True`, client's request timeout to 20 sec.
3. Removes excess casts to float32 left in Dmitry's code.
4. (minor) Improves error messages.
The goals of these changes are:
- Make Petals work in Colab right after just doing `pip install -r requirements.txt`
- Make tests work independently of the protobuf package version chosen while installing dependencies
- Before this PR, `ServerState.JOINING` was announced only once. This announcement quickly expires in case of the full-size BLOOM, since loading blocks takes several minutes. This PR fixes it, so `ServerState.JOINING` is announced periodically in a thread until blocks are loaded.
- This PR also makes the `Server` class a non-thread, so it runs in the main thread and can catch `KeyboardInterrupt`. This is important, since if we are downloading blocks right now, we need to stop it and send the `ServerState.OFFLINE` message. Note that `ModuleContainer` is still a thread.
- (minor) For the sake of readability, I moved the `ModuleContainer.create()` definition, so it is now defined before `Server.__init__()` (this is because `.create()` is invoked first).
This PR makes servers and clients use public swarm's bootstrap peers if no other initial peers are specified.
If you'd like a server to start a new swarm, provide the `--new_swarm` CLI argument.
- run_server now accepts model name as both positional and keyword argument
- changed names in README to account for interface updates
- moved model conversion from README to a separate wiki page
- updated requirements.txt
* update dependency versions
* install bitsandbytes cpuonly from pip
* remove deprecated API from task pool
* clearer startup logs
Co-authored-by: Tim Dettmers <dettmers@cs.washington.edu>
* priority in handlers and backend pools
* simple points system on server side
* priortize task in handler before submit task
* fix tests
* s/expert/block/g
Co-authored-by: justheuristic <justheuristic@gmail.com>
Previously, attempting to allocate with MemoryCache that does not have enough space would throw AllocationFailed.
PR changes this behavior to the following:
- by default, wait until memory is freed by other tenants (FIFO)
- if could not allocate within timeout, throw AllocationFailed
- if allocated size is too big to fit even in empty cache, throw AllocationFailed
- [x] passes existing tests
- [x] passes manual load tests
p.s. if anyone wondered: using mp.Condition will not make the code simpler, their lock behavior is slightly different to what we need here
Co-authored-by: Alexander Borzunov <hxrussia@gmail.com>
Co-authored-by: Aleksandr Borzunov <borzunov.alexander@gmail.com>
- Maximum length is now provided in `.inference_session(max_length=100)`
- previously, we would always assume max length = 2048
- added a generic way to forward **kwargs to inference session
- for compatibility with #47
- Note to @borzunov : it does *not* pass them arbitrarily, but instead checks for kwarg names at the bottom level
- run_server can be started with a custom max_length for inference
- renamed --cache_size_bytes to --attention_cache_bytes (to avoid collision with --cache_dir)
- --attn_cache_bytes can now support humane file sizes (e.g. 300MB instead of 314572800)
- made some server-side errors more human-readable to user (e.g. when max length is exceeded)
Co-authored-by: Aleksandr Borzunov <borzunov.alexander@gmail.com>
Co-authored-by: Alexander Borzunov <hxrussia@gmail.com>