Repository navigation
Explain DeepInfer-Lab's experimental research philosophy - #12
Merged
Merged
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The READMEs still led with a small readable reimplementation after the project was renamed. Reframe both languages around rebuilding inference systems from first principles: start with a correct baseline, profile a bottleneck, test a design hypothesis, verify correctness, and measure kernel and end-to-end effects and trade-offs.
Put the fixed 4 × B200 prefill scope and public experimental process up front; connect the documented 3.98× improvement to its reports; add the planned FlashMLA, DeepGEMM and DeepEP reimplementations. Move community information and the dated status notice below the roadmap, and describe Inferact collaboration and decode resources as future possibilities.
Validation: all 50 local README links and anchors resolve; existing performance, correctness, architecture, usage and hardware sections are unchanged; planned work is explicitly marked;
git diff --checkpasses. Documentation only.