lm-sys / lm-sys/FastChat

CUDA error with parameter --num-gpus 2

Open
#1,389 6 comments 3 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
39.5k
Forks
4.8k
PR merge metrics
No merged PRs in 30d

Description

GPUs: 2 x RTX 4090 24G
run below command: python3 -m fastchat.serve.cli --model-path ~/vicuna-13b-1_1-hf/ --num-gpus 2
All it's ok before i input prompt, I tried to input "hello", get below error:

RuntimeError: CUDA error: device-side assert triggered
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.

How to fix it?

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

Start with the reported command, python3 -m fastchat.serve.cli --model-path ~/vicuna-13b-1_1-hf/ --num-gpus 2, and reproduce the failure after entering "hello". Run it with CUDA_LAUNCH_BLOCKING=1 to obtain a more useful traceback; done means identifying and fixing the multi-GPU prompt failure so the command completes successfully.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
cli, machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.