Add nvtriton (Triton TileIR backend) to helion Dockerfile#461
Merged
msaroufim merged 1 commit intogpu-mode:mainfrom Mar 11, 2026
Merged
Add nvtriton (Triton TileIR backend) to helion Dockerfile#461msaroufim merged 1 commit intogpu-mode:mainfrom
msaroufim merged 1 commit intogpu-mode:mainfrom
Conversation
Install nvtriton wheel from GitHub Release v3.6.0-rc1 after PyTorch, replacing the upstream triton==3.6.0 that ships with PyTorch cu130. Set ENABLE_TILE=1 to activate the TileIR compiler backend by default. Verified on B200 (sm100): - TileIRDriver activation: OK - tileiras embedded discovery: OK - Triton dot kernel (fp16 64x64): max diff 0.0 - Helion matmul (fp16 256x256): max diff 0.0 - IR pipeline: convert-triton-to-cuda-tile → cuda_tile.module confirmed - Helion test suite (HELION_BACKEND=tileir): 834 passed, 463 skipped, 0 failed
Contributor
Author
Build & test logs for reviewersFull Docker build log and helion test suite log attached for your convenience: Contents:
Tested on NVIDIA B200 (sm100, compute capability 10.0). |
msaroufim
approved these changes
Mar 11, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
triton==3.6.0that ships with PyTorch cu130 (same package nametriton, drop-in compatible)ENABLE_TILE=1to activate the TileIR backend by defaultWhat is nvtriton / TileIR?
TileIR is an alternative compiler backend for Triton that lowers Triton IR to the
cuda_tiledialect, then compiles viatileiras. It ships with embedded CUDA dependencies (ptxas,tileiras,libnvvm) so no external CUDA toolkit is needed for compilation.Changes
Single Dockerfile change: after PyTorch install, before Helion install:
Test plan
All verified inside the built Docker image on NVIDIA B200 (sm100):
docker build --no-cache -f docker/helion.Dockerfile -t helion-tileir .— OKfrom triton.runtime.driver import driver; type(driver.active).__name__→TileIRDriverTileIREnvConf.get_tileiras_path()→.../cuda_dep_x86/bin/tileirasmax diff: 0.0✅max diff: 0.0✅convert-triton-to-cuda-tile→cuda_tile.module→fuse-fma→strip-debuginfoconfirmedHELION_BACKEND=tileir ENABLE_TILE=1 pytest -n4 -rf --timeout=60 --ignore=test/test_examples_dist.py .): 834 passed, 463 skipped, 0 failed (109s)import helion→ OKDocker build log (excerpt)