microsoft / microsoft/VPTQ

Does not work in Oobabooga

Open
#53 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

inference question
Dominant language
Python
Stars
681
Forks
53
PR merge metrics
No merged PRs in 30d

Description

Hello,

I downloaded this last night:

VPTQ-community_Meta-Llama-3.1-405B-Instruct-v16-k65536-1024-woft

I ran it in Oobabooga. It loaded fine. But when I tried to talk to the model (chat-instruct) nothing happened. I ran nvidia-smi and it looked like the model loaded but no inferencing was going on.

I also did the same for other V8 and V16 models and they did not work in Oobabooga as well.

I don't have to use Oobabooga....I can use other programs such as Kobold if they work better?

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 by reproducing the reported VPTQ-community_Meta-Llama-3.1-405B-Instruct-v16-k65536-1024-woft behavior in Oobabooga and inspect nvidia-smi while attempting chat-instruct inference. Compare the same behavior with the reported V8 and V16 models and determine whether another supported program can run them; done means inference works or the incompatibility is documented with reproduction details.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.