flagos-ai / flagos-ai/FlagTree

[Kunlunxin] 昆仑芯XPU 使用flagtree 编译Triton Attention 后端报错了

Open
#922 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
350
Forks
149
Avg merge
2d 4h
Merged PRs (30d)
81

Description

flagtree 编译 vllm 0.20.0 的 triton attention 后端报错了
复现环境
- 镜像: 使用flagtree xpu 3.6 镜像安装vllm 0.20.0 即可。可以把TRITON_ATTN 对应的 triton kernel 拿出来验证一下。

详细日志如下:
[昆仑芯用flagtree 编译TRITON_ATTN后端报错.txt](https://github.com/user-attachments/files/30774319/flagtree.TRITON_ATTN.txt)

Contributor guide

Open the contributing guide

Research direction

Start by reproducing the failure in the FlagTree XPU 3.6 image with vLLM 0.20.0, then read the attached log and isolate the TRITON_ATTN Triton kernel as suggested. Done means the TRITON_ATTN backend compiles successfully in that environment without the reported error.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
compilers
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.