[EagerJIT] Update README example to eager jit#1752
Conversation
|
👋 Hi! Thank you for contributing to the TileLang project. Please remember to run We appreciate you taking this step! Our team will review your contribution, and we look forward to your awesome work! 🚀 |
📝 WalkthroughWalkthroughThe README example refactors a matmul function to matmul_relu, transitioning from parameter-based inputs (M, N, K) to explicit tensor arguments (A, B), adding ReLU operation, and shifting return semantics from a kernel object to the computed output tensor. Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Fix all issues with AI agents
In `@README.md`:
- Around line 157-185: The example uses T.ceildiv(...) and tile buffers
(A_shared, B_shared, C_local) with T.copy/T.gemm/T.clear but lacks edge-tile
bounds protection, so add explicit per-tile boundary guards or masking before
any global memory loads/stores: check tile-global ranges computed from bx/by/ko
against M/N/K and only copy valid elements into A_shared/B_shared and only write
valid elements from C_local back via the final T.copy, and also guard the relu
loop over i,j to skip out-of-range indices; alternatively, update the README
example text to state that M, N, and K must be exact multiples of block_M,
block_N, and block_K and call out that the current code requires this
divisibility.
2 participants
as title
Summary by CodeRabbit
✏️ Tip: You can customize this high-level summary in your review settings.