github.com Sep 19
GitHub - Neroued/ninfer: High-performance single-GPU inference for selected model checkpoints and GPUs.
github.com/Neroued/ninfer
Story Details
| Last Updated | |
| Total Articles | 2 |
Main Topics
specialized electronic circuit; graphics accelerator
Similar to This
Previous
github.com Oct 06
GitHub - lkarlslund/ninfer6000: High-performance single-GPU inference for selected model checkpoints and GPUs.
github.com/lkarlslund/ninfer6000
github.com Oct 02
GitHub - giveen/KernelOPT: Dispatch-aware agentic GPU kernel optimization: Dispatch-aware agentic GPU kernel optimization. Contribute to giveen/KernelOPT ...
github.com/giveen/KernelOPT
github.com Sep 26
GitHub - giveen/ninfer-ext: ninfer-ext: Forked for speed.: ninfer-ext: Forked for speed. Contribute to giveen/ninfer-ext development by creating an account on ...
github.com/giveen/ninfer-ext
github.com Sep 11
GitHub - giveen/ninfer-studio: Desktop UI for the NInfer local LLM inference engine
github.com/giveen/ninfer-studio
github.com Aug 21
GitHub - mr-september/ninfer-2080ti-22g: High-performance single-GPU inference for selected model checkpoints and GPUs.
github.com/mr-september/ninfer-2080ti-22g
github.com Aug 16
GitHub - UDPSendToFailed/ninfer-4090: Ninfer port for Qwen 3.8 27B on RTX 4090: Ninfer port for Qwen 3.8 27B on RTX 4090. Contribute to ...
github.com/UDPSendToFailed/ninfer-4090
Next