memra-engine 0.83.0

From-scratch CUDA LLM inference engine for NVIDIA RTX 50-series (sm_120a) and Hopper (sm_90a) - custom kernels, no frameworks

Coverage
57.3%
891 out of 1555 items documented0 out of 888 items with examples
Size
Source code size: 6.44 MB This is the summed size of all the files inside the crates.io package for this release.
Documentation size: 17.97 MB This is the summed size of all files generated by rustdoc for all configured targets
Ø build duration
this release: 8s Average build duration of successful builds.
all releases: 10s Average build duration of successful builds in releases after 2024-10-23.
Links
avifenesh/memra
304 35 0
crates.io
Dependencies
Versions
Owners

memra engine: Stage-1 correctness-first forward-pass kernels + ops, on sm_120 via cudarc.