DeepSeek-V4.1-Flash inference on NVIDIA Ampere with vLLM, SM80 patches, reproducible throughput and coding-agent benchmarks. Tested on 8x A800 80GB.
-
Updated
Sep 15, 2026 - Python
DeepSeek-V4.1-Flash inference on NVIDIA Ampere with vLLM, SM80 patches, reproducible throughput and coding-agent benchmarks. Tested on 8x A800 80GB.
Density-Calibrated Kernel Drifting for one-step ImageNet generation in JAX, with A800 configs and frozen 50k evaluation results.
To associate your repository with the a800 topic, visit your repo's landing page and select "manage topics."