[PR #5854] [MERGED] Refine error reporting for subprocess crash #74236

Closed
opened 2026-05-05 06:14:02 -05:00 by GiteaMirror · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/5854
Author: @dhiltgen
Created: 7/22/2024
Status: Merged
Merged: 7/22/2024
Merged by: @dhiltgen

Base: mainHead: win_exit_status


📝 Commits (1)

  • a3c20e3 Refine error reporting for subprocess crash

📊 Changes

1 file changed (+12 additions, -9 deletions)

View changed files

📝 llm/server.go (+12 -9)

📄 Description

On windows, the exit status winds up being the search term many users search for and end up piling in on issues that are unrelated. This refines the reporting so that if we have a more detailed message we'll suppress the exit status portion of the message.

Example:

Before

> ollama run akuldatta/mistral-nemo-instruct-12b:q5km
Error: llama runner process has terminated: exit status 0xc0000409 error loading model: check_tensor_dims: tensor 'blk.0.attn_q.weight' has wrong shape; expected  5120,  5120, got  5120,  4096,     1,     1

After:

> ollama run akuldatta/mistral-nemo-instruct-12b:q5km
Error: llama runner process has terminated: error loading model: check_tensor_dims: tensor 'blk.0.attn_q.weight' has wrong shape; expected  5120,  5120, got  5120,  4096,     1,     1

This should reduce the amount of users posting unrelated problems on whatever open issue(s) happen to have 0xc0000409 in the title.


🔄 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/5854 **Author:** [@dhiltgen](https://github.com/dhiltgen) **Created:** 7/22/2024 **Status:** ✅ Merged **Merged:** 7/22/2024 **Merged by:** [@dhiltgen](https://github.com/dhiltgen) **Base:** `main` ← **Head:** `win_exit_status` --- ### 📝 Commits (1) - [`a3c20e3`](https://github.com/ollama/ollama/commit/a3c20e3f181607760ee86893baaf31b3c7fd3012) Refine error reporting for subprocess crash ### 📊 Changes **1 file changed** (+12 additions, -9 deletions) <details> <summary>View changed files</summary> 📝 `llm/server.go` (+12 -9) </details> ### 📄 Description On windows, the exit status winds up being the search term many users search for and end up piling in on issues that are unrelated. This refines the reporting so that if we have a more detailed message we'll suppress the exit status portion of the message. Example: Before ``` > ollama run akuldatta/mistral-nemo-instruct-12b:q5km Error: llama runner process has terminated: exit status 0xc0000409 error loading model: check_tensor_dims: tensor 'blk.0.attn_q.weight' has wrong shape; expected 5120, 5120, got 5120, 4096, 1, 1 ``` After: ``` > ollama run akuldatta/mistral-nemo-instruct-12b:q5km Error: llama runner process has terminated: error loading model: check_tensor_dims: tensor 'blk.0.attn_q.weight' has wrong shape; expected 5120, 5120, got 5120, 4096, 1, 1 ``` This should reduce the amount of users posting unrelated problems on whatever open issue(s) happen to have `0xc0000409` in the title. --- <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 2026-05-05 06:14:02 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#74236