← Back to Discover
avifenesh

avifenesh/bw24

RustMITactiverising
89Health

From-scratch Rust+CUDA inference engine, bit-exact by construction — NVFP4, MoE, MTP speculative decoding, tuned against measured limits of one RTX 5090 Laptop (sm_120a).

Stars257
Forks30
Open Issues0
Contributors30
Last Push0d ago

Health Breakdown

Activity
25
Community
25
Maintenance
14
Popularity
25
#blackwell#cuda#gguf#gpu-kernels#llama-cpp#llm-inference#moe#nvfp4#rust#speculative-decoding
View on GitHub ↗Issues (0) ↗Pull Requests ↗Wiki ↗

Should you contribute to avifenesh/bw24?

avifenesh/bw24 has a FoundDev health score of 89/100, which puts it in the active-and-maintained tier. The maintainer team is shipping recently, issues are being closed, and a PR you open this week has a realistic chance of being reviewed.

Last push was 0 days ago — that signals an actively maintained project. New issues are likely to get a maintainer response within days. The project is written primarily in Rust, so prior Rust experience will shorten ramp-up.

Licensed under MIT, a standard OSI-approved license — safe to contribute to under normal employer IP policies.

Community

avifenesh89

From-scratch Rust+CUDA inference engine, bit-exact by construction — NVFP4, MoE, MTP speculative decoding, tuned against measured limits of one RTX 5090 Laptop (sm_120a).

activerising
25730 contributors
0d ago

More Rust repos

libra-tools
libra-tools/libra
Libra is evolving into an AI agent–native version control tools
7896
dfinity
dfinity/examples
Example applications, microservices, and code samples for the Internet Computer
61195
dragonflyoss
dragonflyoss/client
Dragonfly client written in Rust
6993