thu-ml / thu-ml/TurboDiffusion

Reproducing results on RTX 5090 (sm120): SpargeAttention compatibility and environment setup

Open
#91 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
3.7k
Forks
277
Avg merge
2h 57m
Merged PRs (30d)
2

Description

Hi, thanks for the great work.

I'm trying to reproduce this on an RTX 5090, but I'm stuck at installing SpargeAttention. It appears the repo lacks support for sm120, causing sagesla to fail.

Could you share your exact environment config (Python/CUDA versions)? Also, is there a known workaround to make this work on the RTX 5090? Thanks!

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

The issue mentions SpargeAttention, sagesla, and an RTX 5090 with sm120 support, but names no files or tests. Start by checking the installation path and environment requirements, then verify whether the documented Python/CUDA configuration or a confirmed RTX 5090 workaround resolves the failure.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai-infra-agents, machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.