[Unity][MSC][M3.2] Add gym for pruning and quantization, enable auto prune/quantize#16280
Merged
Hzfengsy merged 2 commits intoapache:unityfrom Dec 31, 2023
Merged
[Unity][MSC][M3.2] Add gym for pruning and quantization, enable auto prune/quantize#16280Hzfengsy merged 2 commits intoapache:unityfrom
Hzfengsy merged 2 commits intoapache:unityfrom
Conversation
Hzfengsy
approved these changes
Dec 28, 2023
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This is a pull request for MSC(Multi-System Compile)
RFC: https://discuss.tvm.apache.org/t/rfc-unity-msc-introduction-to-multi-system-compiler/15251/5
Tracking issue: #15233
This is the Milestone 3 for MSC: Add MSCGym, enable auto compression. Add distiller, enable knowledge distilliation.
To limit each PR in reviewable size, the Milestone 3 will be split into some steps:
M3.1 Add distiller for distill model
M3.2 Add gym for pruning and quantization, enable auto prune/quantize
Gym in MSC works like auto tvm in tvm. It extract tasks from tools and search the best policy for apply pruning/quantization. The design of gym is similar with OpenAI Gym: https://github.com/openai/gym. It defines the optimization process as "envs" and search methods as "agents". More than one agents can work together with one env.
cc @Hzfengsy