-
Stefy Lanza (nextime / spora ) authored- Add generate_chat() and generate_chat_stream() methods to VulkanBackend - These use create_chat_completion() which properly applies model's chat template - Fallback to manual formatting if create_chat_completion fails - Update API endpoints to pass messages dict directly instead of formatted prompt - Fixes garbled output with Qwen3 and other models that use custom chat templates
7947fb75
| Name |
Last commit
|
Last update |
|---|---|---|
| __pycache__ | ||
| LICENSE.md | ||
| README.md | ||
| build.sh | ||
| coder | ||
| coderai | ||
| requirements-nvidia.txt | ||
| requirements-vulkan.txt | ||
| requirements.txt |