github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #7594] [CLOSED] Invalid OLLAMA_LLM_LIBRARY Error #23004

New Issue
Closed
opened 2026-04-19 16:42:53 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-19 16:42:53 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/7594
Author: @jk-vtp-one
Created: 11/10/2024
Status: ❌ Closed

Base: main ← Head: dev

📝 Commits (1)

  • d3f003f Invalid OLLAMA_LLM_LIBRARY error

📊 Changes

1 file changed (+1 additions, -0 deletions)

View changed files

📝 llm/server.go (+1 -0)

📄 Description

If the OLLAMA_LLM_LIBRARY environment variable is an invalid target, currently the server logs a message of the problem and continues to work using another available runner. This change causes it instead to raise an error. If you are using the OLLAMA_LLM_LIBRARY variable, you should intend for it to use that runner, and if that runner isn’t available it should error, not fall back to something else.

The specific use case is from the testing of the ollama builder with jetson-containers. Previous versions of the ollama build process included the env variable: OLLAMA_SKIP_CPU_GENERATE which allowed us to only generate the CUDA runner. If the binary build process completed but the cuda runner failed to build, our test would fail due to there being no available runners. Now, trying to use OLLAMA_LLM_LIBRARY with the desired but failed-to-build cuda_vXX runner, it falls back to use the CPU runner and the test doesn’t fail.

Re-implementing the build variables OLLAMA_SKIP_CPU_GENERATE and OLLAMA_SKIP_CUDA_GENERATE, would work: https://github.com/ollama/ollama/pull/7499; but doesn’t change that targeting an invalid OLLAMA_LLM_LIBRARY should error.

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/ollama/ollama/pull/7594 **Author:** [@jk-vtp-one](https://github.com/jk-vtp-one) **Created:** 11/10/2024 **Status:** ❌ Closed **Base:** `main` ← **Head:** `dev` --- ### 📝 Commits (1) - [`d3f003f`](https://github.com/ollama/ollama/commit/d3f003f56d106df5f511f976e3bdf87b89588fe9) Invalid OLLAMA_LLM_LIBRARY error ### 📊 Changes **1 file changed** (+1 additions, -0 deletions) <details> <summary>View changed files</summary> 📝 `llm/server.go` (+1 -0) </details> ### 📄 Description If the OLLAMA_LLM_LIBRARY environment variable is an invalid target, currently the server logs a message of the problem and continues to work using another available runner. This change causes it instead to raise an error. If you are using the OLLAMA_LLM_LIBRARY variable, you should intend for it to use that runner, and if that runner isn’t available it should error, not fall back to something else. The specific use case is from the testing of the ollama builder with jetson-containers. Previous versions of the ollama build process included the env variable: OLLAMA_SKIP_CPU_GENERATE which allowed us to only generate the CUDA runner. If the binary build process completed but the cuda runner failed to build, our test would fail due to there being no available runners. Now, trying to use OLLAMA_LLM_LIBRARY with the desired but failed-to-build cuda_vXX runner, it falls back to use the CPU runner and the test doesn’t fail. Re-implementing the build variables OLLAMA_SKIP_CPU_GENERATE and OLLAMA_SKIP_CUDA_GENERATE, would work: https://github.com/ollama/ollama/pull/7499; but doesn’t change that targeting an invalid OLLAMA_LLM_LIBRARY should error. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
GiteaMirror added the pull-request label 2026-04-19 16:42:53 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label pull-request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#23004
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?