[Bug]: Parallel Embedding is not working on Windows Servers
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 3.2k
- Forks
- 249
- Avg merge
- 4d 8h
- Merged PRs (30d)
- 4
Description
What happened?
I am trying to encode my dataset with multiple CUDA GPU but only one GPU is working
What is the expected behaviour?
all specified 4 GPU must work
A minimal reproducible example
embedding_model = LateInteractionTextEmbedding("jinaai/jina-colbert-v2",cuda=True,device_ids=[0,1,2,3])
descriptions_embeddings = list(embedding_model.embed(documents,parallel=4))
What Python version are you on? e.g. python --version
python3.11
FastEmbed version
v0.4.2
What os are you seeing the problem on?
No response
Relevant stack traces and/or logs
No response
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the provided LateInteractionTextEmbedding example and its embed(documents, parallel=4) entry point, using device_ids=[0,1,2,3] on a Windows server. Reproduce the issue with Python 3.11 and FastEmbed v0.4.2, then trace the parallel embedding and CUDA device handling. Done means all four specified GPUs process the workload rather than only one.
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
- Mostly clear
- Newbie friendliness
- 35/100