A narrow native inference engine for running DeepSeek V4 Flash and other selected large models on consumer Metal, CUDA and ROCm hardware.
23.9K2.3KCMITUpdated 8 hours ago
#rocm
Curated GitHub repositories related to rocm, with AI summaries and key stats.
A narrow native inference engine for running DeepSeek V4 Flash and other selected large models on consumer Metal, CUDA and ROCm hardware.