Popular repositories Loading

1. EnvisionOS EnvisionOS Public

   envision os repository

2. legacy-gpu-llm-notes legacy-gpu-llm-notes Public

   Measured llama.cpp and quantization results on Tesla V100 (sm_70), Pascal GTX 1070, and RTX 4070 - hardware most projects don't test on

   Python

3. volta-bonsai volta-bonsai Public

   Ternary-Bonsai-2-27B on a Tesla V100 (sm_70): ternary kernels and vision both work on Volta

   Shell

4. volta-gpt-oss volta-gpt-oss Public

   gpt-oss-20b MXFP4 runs on a Tesla V100 (sm_70) at 143 t/s, despite MXFP4 being documented as requiring compute capability 9.0+

5. volta-ik-llama volta-ik-llama Public

   ik_llama.cpp builds clean and runs correctly on a Tesla V100 (sm_70) with no source changes

6. volta-dual-card volta-dual-card Public

   Mixed sm_70 + sm_89 layer split in one llama.cpp job: works, cheap, no VRAM leak