Experimental NVIDIA tensor-compute unlock research: guarded TU102 initramfs port, offline tests, and Ampere reproduction notes
Repository Index
72,362 visible repositories in the index
1–5 of 5 · Most stars
llama.cpp fork for significantly improved performance on Ampere generation Nvidia cards (especially RTX 3090 / 3090 Ti): example: 110+ tok/s over a 100K-token generation at temperature 1 for qwen3.8, supporting full 262K ctx. Supports low memory (12gb) configs for 200k+ ctx. 120+ TPS, 3300+ prefill for QFN 3.8.
- ampere
- consumer-gpu
- cuda
- ggml
Deepinfer inspired implemetation on SM80 Ampere architecture. Deepest respect for DeepSeek opensource this work!
Enable SR-IOV vGPU for consumer Ampere and Ada GeForce cards.
- dkms
- geforce
- gpu-virtualization
- homelab
Ampere's CPU Performance Model
- analysis
- microarchitecture
- performance-modeling
- processor-simulator