Qwen2.5-Coder default + automatic GPU (CUDA/Metal/CPU) backend - #1
Open
godsonj64 wants to merge 1 commit into
Open
Qwen2.5-Coder default + automatic GPU (CUDA/Metal/CPU) backend#1godsonj64 wants to merge 1 commit into
godsonj64 wants to merge 1 commit into
Conversation
Bring the repo up to date with the local working tree. Key changes: - Default model -> Qwen2.5-Coder-3B-Instruct (Q4_K_M, ~2GB), the best small stable coding model; llama-server sampling adjusted to suit it. - Automatic llama.cpp backend selection: CUDA (NVIDIA, toolkit version matched to the GPU's compute capability), Metal (Apple Silicon), else CPU. Includes Windows cudart runtime handling and automatic CPU->GPU upgrade on relaunch. - Adds llama-installer + headless tests, GitHub integration, renderer updates, and the trailer toolkit.
godsonj64
force-pushed
the
feat/qwen-default-cuda-backend
branch
from
July 6, 2026 22:22
199da05 to
5613496
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Brings the repo up to date with the local working tree.
Highlights
cudartruntime and auto-upgrades CPU→GPU on relaunch.llama-installer+ headless tests, GitHub integration, renderer updates, trailer toolkit.Verification
node scripts/llama_installer_test.js→ 30/30 pass.