GitLab

Marlin quantized linear only supports GPU device, when change generate_op
to "KLinearMarlin", generate_device need to be changed to "cuda" accordingly.

Fixes: e5b001d7 ("Update readme; Format code; Add example yaml.")

use marlin for lm_head, lm_head only calc last token for prefill
extend context window to 19K for DeepSeek-V3/R1 within 24GB VRAM

[fix] fix ktransformers interface when use new CUDAGraphRunner
[fix] fix YAML and optimize logic, the top rule has the highest priority

support windows support q4_0 and q5_0 dequant on cpu Add CopyRight from pygguf(It was added before, but disappear after merge). Add some TODO in the code.