Proposal to enable privacy-enhanced preloading
7 daysStars20024h gain0Score0.0
Find trending repositories by name or description.
Proposal to enable privacy-enhanced preloading
Revizor - Hardware fuzzing for the age of speculation
Qwen 3.8 27B ROCmFP4 on AMD Strix Halo (Ryzen AI Max+ 395). Up to 36 tok/s via MTP Speculation, TurboQuant & Mesa RADV Wave64.
MobiInfer runs 35B-A3B-class MoE models fully on-device on the Qualcomm Hexagon NPU, streaming experts from flash with lookahead scheduling (LES) and DSpark speculation.