Available unified memory in llama.cpp
Nobody has claimed this yet.
- Dominant language
- Go
- Stars
- 651
- Forks
- 155
- PR merge metrics
- No merged PRs in 30d
Description
There is a bug (Misc. bug: UMA detection incorrectly limits available memory on AMD APUs with large TTM allocations) with reporting available shared memory for integrated GPUs (at least, AMD GPUs).
This bug is also present in llama.cpp models pulled with Docker Model Runner.
The workaround for this bug for an Ollama container that I use is:
ollama:
# Vulkan, rather than ROCM (image: ollama/ollama:rocm):
image: ollama/ollama:latest
environment:
GGML_CUDA_ENABLE_UNIFIED_MEMORY: 1
OLLAMA_VULKAN: 1
OLLAMA_IGPU_ENABLE: 1
How can I similarly configure in docker-compose.yml a model run by Docker Model Runner?
Contributor guide
No contributing guide indexed for this repository
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 Docker Model Runner configuration path and the docker-compose.yml setup described in the issue. Compare the linked llama.cpp behavior and the Ollama environment-variable workaround to determine whether an equivalent setting is supported or needs to be exposed. Done means documenting or enabling a clear configuration for unified memory in Docker Model Runner.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- docker, docker-compose
- Domain
- devops, infrastructure
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 45/100