Permalink
Comparing changes
Choose two branches to see what’s changed or to start a new pull request.
If you need to, you can also or
learn more about diff comparisons.
Open a pull request
Create a new pull request by comparing changes across two branches. If you need to, you can also .
Learn more about diff comparisons here.
...
- 3 commits
- 121 files changed
- 7 contributors
Commits on Mar 2, 2023
-
fix: out of order message delivery (#354)
In order to minimize the blocking of asynchronous I/O tasks when a large number of message chunks (e.g., model size is large) need to be assembled, threading is used. This led to a bug wherein messages are delivered to a receive queue in an out-of-order fashion. For example, consider two back-to-back messages; the first message is larger than the second. In this case, the second can be inserted before the first because the second has high chance to finish the assembling. The changes here are for fixing the bug. To do so, we leverage another queue to synchronize message delivery order. For that, chunk manager class is introduced. One chunk manager is created for a backend. And it maintains a list of chunk threads per end, each of which is responsible for assemling messages sequentially and pushing them into the receive queue of the end.
-
gpu and cpu compatibility pytorch (#350)
This modification will allow trainers/aggregators to work on different devices across different machines. Basically, all weights are communicated by placing them on the CPU before serializing them. Then, they are moved back to the device where they were previously. All trainers now require a self.model attribute and all middle aggregators must only use the CPU (not enforced).
Commits on Mar 6, 2023
-
* Add group associations to roles (#319) * Sync up the generated code from openapi generator with what we have currently (#331) * applied formatting (#341) * pre-commit setup and dev reqs (#342) * Refactor config handling with pydantic (#332) * Make sdk config backwards compatible. (#355) * Fix merge conflicts between development and main branch (#353) * optimizer compatibility with tensorflow and example for medmnist keras/pytorch (#320) Tensorflow compatibility for new optimizers was added, which included fedavg, fedadam, fedadagrad, and fedyogi. A shell script for tesing all 8 possible combinations of optimizers and frameworks is included. This allows the medmnist example to be run with keras (the folder structure was refactored to include a trainer and aggregator for keras). The typo in fedavg.py has now been fixed. * feat+fix: grpc support for hierarchical fl (#321) Hierarchical fl didn't work with grpc as backend. This is because groupby field was not considered in metaserver service and p2p backend. In addition, a middle aggregator hangs even after a job is completed. This deadlock occurs because p2p backend cleanup code is called as a part of a channel cleanup. However, in a middle aggregator, p2p backend is responsible for tasks across all channnels. The p2p cleanup code couldn't finish cleanup because a broadcast task for in the other channel can't finish. This bug is fixed here by getting the p2p backend cleanup code out side of channel cleanup code. * documenation for metaserver/mqtt local (#322) Documentation for using metaserver will allow users to run examples with a local broker. It also allows for mqtt local brokers. This decreases the chances of any job ID collisions. Modifications to the config.json for the mnist example were made in order to make it easier to switch to a local broker. The readme does indicate how to do this for other examples now. Co-authored-by: vboxuser <vboxuser@Ubuntu.myguest.virtualbox.org> * feat: asynchronous fl (#323) Asynchronous FL is implemented for two-tier topology and three-tier hierarchical topology. The main algorithm is based on the following two papers: - https://arxiv.org/pdf/2111.04877.pdf - https://arxiv.org/pdf/2106.06639.pdf Two examples for asynchronous fl are also added. One is for a two-tier topology and the other for a three-tier hierarchical topology. This implementation includes the core algorithm but doesn't include SecAgg algorithm (presented in the papers), which is not the scope of this change. * fix+refactor: asyncfl loss divergence (#330) For asyncfl, a client (trainer) should send delta by subtracting local weights from original global weights after training. In the current implementation, the whole local weights were sent to a server (aggregator). This causes loss divergence. Supporting delta update requires refactoring of aggregators of synchronous fl (horizontal/{top_aggregator.py, middle_aggregator.py}) as well as optimizers' do() function. The changes here support delta update universally across all types of modes (horizontal synchronous, asynchronous, and hybrid). * fix: conflict bewtween integer tensor and float tensor (#335) Model architectures can have integer tensors. Applying aggregation on those tensors results in type mistmatch and throws a runtime error: "RuntimeError: result type Float can't be cast to the desired output type Long" Integer tensors don't matter in back propagation. So, as a workaround to the issue, we typecast to the original dtype when the original type is different from the dtype of weighted tensors for aggregation. In this way, we can keep the model architecture as is. * refactor: config for hybrid example in library (#334) To enable library-only execution for hybrid example, its configuration files are updated accordingly. The revised configuration has local mqtt and p2p broker config and p2p broker is selected. * misc: asynchronous hierarchical fl example (#340) Since the Flame SDK supports asynchronous FL, we add an example of an asynchronous hierarchical FL for control plane. * chore: clean up examples folder (#336) The examples folder at the top level directory has some outdated and irrelevant files. Those are now removed from the folder. * fix: workaround for hybrid mode with two p2p backends (#345) Due to grpc/grpc#25364, when two p2p backends (which rely on grpc and asyncio) are defined, the hybrid mode example throws an execption: 'BlockingIOError: [Errno 35] Resource temporarily unavailable'. The issue still appears unresolved. As a temporary workaround, we use two different types of backends: mqtt for one and p2p for the other. This means that when this example is executed, both metaserver and a mqtt broker (e.g., mosquitto) must be running in the local machine. * fix: distributed mode (#344) Distributed mode has a bug: before 'weights' is not defined as member variable, deepcopy(self.weights) in _update_weights() is called. To address this issue, self.weights is initialized in __init__(). Also, to run a distributed example locally, configuration files are revised. * example/implementation for fedprox (#339) This example is similar to the ones seen in the fedprox paper, although it currently does not simmulate stragglers and uses another dataset/architecture. A few things were changed in order for there to be a simple process for modifying trainers. This includes a function in util.py and another class variable in the trainer containing information on the client side regularizer. Additionally, tests are automated (mu=1,0.1,0.01,0.001,0) so running the example generates or modifies existing files in order to provide the propper configuration for an experiment. * Create diagnose script (#348) * Create diagnose script * Make the script executable --------- Co-authored-by: Alex Ungurean <aungurea@cisco.com> * refactor+fix: configurable deployer / lib regularizer fix (#351) deployer's job template file is hard-coded, which makes it hard to use different template file at deployment time. Using different different template file is useful when underlying infrastructure is different (e.g., k8s vs knative). To support that, template folder and file is fed as config variables. Also, deployer's config info is fed as command argument, which is cumbersome. So, the config parsing part is refactored such that the info is fed as a configuration file. During the testing of deployer change, a bug in the library is identified. The fix for it is added here too. Finally, the local dns configuration in flame.sh is updated so that it can be done correctly across different linux distributions (e.g., archlinux and ubuntu). The tests for flame.sh are under archlinux and ubuntu. * Add missing merge fix * Make sdk config backwards compatible. (#355) --------- Co-authored-by: GustavBaumgart <98069699+GustavBaumgart@users.noreply.github.com> Co-authored-by: Myungjin Lee <myungjin@users.noreply.github.com> Co-authored-by: vboxuser <vboxuser@Ubuntu.myguest.virtualbox.org> Co-authored-by: alexandruuBytex <56033021+alexandruuBytex@users.noreply.github.com> Co-authored-by: Alex Ungurean <aungurea@cisco.com> Co-authored-by: elqurio <119978637+elqurio@users.noreply.github.com> * refactor: end-to-end refactoring (#360) * refactor: end-to-end refactoring The development branch is yet fully tested. Hence, it contains several incompatibility and bugs. The following issues are handled: (1) func tag parsing in config.py (sdk): The config module has a small bug, which the parsed func tags are not populated in Channel class instance. (2) design and schema creation failure (control plane): "name" field in design and "version" field in schema are not used all the time. But they are specified as "required" fields, which causes error during assertion check on these field in openapi code. (3) hyperparameter update failure in mlflow (sdk): hyperparameter is no longer a dictionary, which is an expected format from mlflow. (4) library update for new examples - asyncfl and fedprox (sdk): asyncfl and fedprox algorithms and examples were introduced outside the development branch, which caused compatibility issues. (5) control plane example update (control plane): all the example code in the control plane is outdated because of configuration parsing module changes. (6) README file update in adult and mnist_non_orchestration_mode examples (doc): these two examples are for non-orchestration mode. They will be deprecated. So, a note is added to their README file. * Update lib/python/flame/registry/mlflow.py Co-authored-by: elqurio <119978637+elqurio@users.noreply.github.com> --------- Co-authored-by: openwithcode <123649857+openwithcode@users.noreply.github.com> Co-authored-by: elqurio <119978637+elqurio@users.noreply.github.com> --------- Co-authored-by: elqurio <119978637+elqurio@users.noreply.github.com> Co-authored-by: GustavBaumgart <98069699+GustavBaumgart@users.noreply.github.com> Co-authored-by: Myungjin Lee <myungjin@users.noreply.github.com> Co-authored-by: vboxuser <vboxuser@Ubuntu.myguest.virtualbox.org> Co-authored-by: alexandruuBytex <56033021+alexandruuBytex@users.noreply.github.com> Co-authored-by: Alex Ungurean <aungurea@cisco.com>
7 people authoredMar 6, 2023
Loading
This comparison is taking too long to generate.
Unfortunately it looks like we can’t render this comparison for you right now. It might be too big, or there might be something weird with your repository.
You can try running this command locally to see the comparison on your machine:
git diff v0.2.0...v0.2.1