github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #15836] [CLOSED] Fix qwen35/qwen35moe architecture aliases in llama.cpp parser #77615

New Issue
Closed
opened 2026-05-05 10:17:20 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-05-05 10:17:20 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/15836
Author: @gotnochill815-web
Created: 4/27/2026
Status: ❌ Closed

Base: main ← Head: fix-qwen35-alias

📝 Commits (1)

  • f1dce68 Fix qwen35/qwen35moe architecture aliases

📊 Changes

1 file changed (+8 additions, -0 deletions)

View changed files

📝 llama/llama.cpp/src/llama-arch.cpp (+8 -0)

📄 Description

Summary

Fixes GGUF models that declare qwen35 or qwen35moe architectures.

Problem

Some models failed with:

unknown model architecture: 'qwen35moe'

Although these architecture names were referenced in higher-level Ollama code, the llama.cpp string parser did not recognize them.

Fix

Added compatibility aliases in llm_arch_from_string():

  • qwen35 → LLM_ARCH_QWEN3NEXT
  • qwen35moe → LLM_ARCH_QWEN3NEXT

Validation

Before patch:

  • unknown model architecture: qwen35moe

After patch:

  • ollama show hf.co/unsloth/Qwen3.6-35B-A3B-GGUF:UD-Q4_K_M successfully proceeds and displays metadata.

🔄 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/15836 **Author:** [@gotnochill815-web](https://github.com/gotnochill815-web) **Created:** 4/27/2026 **Status:** ❌ Closed **Base:** `main` ← **Head:** `fix-qwen35-alias` --- ### 📝 Commits (1) - [`f1dce68`](https://github.com/ollama/ollama/commit/f1dce686ac2e53312dfeb8f5d547fcf86373d64f) Fix qwen35/qwen35moe architecture aliases ### 📊 Changes **1 file changed** (+8 additions, -0 deletions) <details> <summary>View changed files</summary> 📝 `llama/llama.cpp/src/llama-arch.cpp` (+8 -0) </details> ### 📄 Description ## Summary Fixes GGUF models that declare `qwen35` or `qwen35moe` architectures. ## Problem Some models failed with: `unknown model architecture: 'qwen35moe'` Although these architecture names were referenced in higher-level Ollama code, the llama.cpp string parser did not recognize them. ## Fix Added compatibility aliases in `llm_arch_from_string()`: * `qwen35` → `LLM_ARCH_QWEN3NEXT` * `qwen35moe` → `LLM_ARCH_QWEN3NEXT` ## Validation Before patch: * `unknown model architecture: qwen35moe` After patch: * `ollama show hf.co/unsloth/Qwen3.6-35B-A3B-GGUF:UD-Q4_K_M` successfully proceeds and displays metadata. --- <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 10:17:20 -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#77615
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?