Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Errors in running test / performance benchmarks #648

Open
rohitnanda1443 opened this issue Oct 8, 2024 · 0 comments
Open

Errors in running test / performance benchmarks #648

rohitnanda1443 opened this issue Oct 8, 2024 · 0 comments

Comments

@rohitnanda1443
Copy link

I installed AMD-Triton using this guide: https://rocm.docs.amd.com/en/latest/how-to/llm-fine-tuning-optimization/model-acceleration-libraries.html

Trying to run the tests:
python perf-kernels/flash-attention.py Traceback (most recent call last): File "/home/rohit/vllm/triton/python/perf-kernels/flash-attention.py", line 28, in <module> import triton File "/home/rohit/miniconda3/envs/vllm/lib/python3.10/site-packages/triton-2.1.0-py3.10-linux-x86_64.egg/triton/__init__.py", line 8, in <module> from .runtime import ( File "/home/rohit/miniconda3/envs/vllm/lib/python3.10/site-packages/triton-2.1.0-py3.10-linux-x86_64.egg/triton/runtime/__init__.py", line 1, in <module> from .autotuner import (Autotuner, Config, Heuristics, OutOfResources, autotune, heuristics) File "/home/rohit/miniconda3/envs/vllm/lib/python3.10/site-packages/triton-2.1.0-py3.10-linux-x86_64.egg/triton/runtime/autotuner.py", line 7, in <module> from ..testing import do_bench, do_bench_cudagraph File "/home/rohit/miniconda3/envs/vllm/lib/python3.10/site-packages/triton-2.1.0-py3.10-linux-x86_64.egg/triton/testing.py", line 8, in <module> from . import language as tl File "/home/rohit/miniconda3/envs/vllm/lib/python3.10/site-packages/triton-2.1.0-py3.10-linux-x86_64.egg/triton/language/__init__.py", line 4, in <module> from . import math File "/home/rohit/miniconda3/envs/vllm/lib/python3.10/site-packages/triton-2.1.0-py3.10-linux-x86_64.egg/triton/language/math.py", line 5, in <module> from . import core File "/home/rohit/miniconda3/envs/vllm/lib/python3.10/site-packages/triton-2.1.0-py3.10-linux-x86_64.egg/triton/language/core.py", line 8, in <module> from .._C.libtriton.triton import ir ImportError: /home/rohit/miniconda3/envs/vllm/bin/../lib/libstdc++.so.6: version GLIBCXX_3.4.30' not found (required by /home/rohit/miniconda3/envs/vllm/lib/python3.10/site-packages/triton-2.1.0-py3.10-linux-x86_64.egg/triton/_C/libtriton.so)
`
help requested to resolve this.

Aim: To get vllm working on a gentoo system.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant