Loreon
Labs
Platform
Docs
Home
Ecosystems
Rust
eLLM
eLLM can infer LLM on CPUs faster than on GPUs
Rust
Emerging
GitHub
Stars
—
Forks
—
Contributors
4
Last push
1mo ago
Recent commits
Latest commits.
Add x86 Qwen3.6 CPU acceleration
16461ef
Anders Cedronius
1mo ago
Improve official Qwen3.6 serving path
fb441a8
Anders Cedronius
1mo ago
Enable x86 AVX512 FP16 intrinsics gate
886c773
Anders Cedronius
1mo ago
Add Qwen3.6 memory preflight
3dc1ff4
Anders Cedronius
1mo ago
Add official Qwen3.6 artifact loading
9400bb7
Anders Cedronius
1mo ago
Add OpenAI-compatible agent endpoint
6fbb630
Anders Cedronius
1mo ago
Mention Apple Silicon in remaining docs
6e4438f
Anders Cedronius
1mo ago
Mention Apple Silicon in README heading
d3d2fda
Anders Cedronius
1mo ago
Top contributors
Builders behind this project.
lucienhuangfu
252 commits
pjasonlyu
23 commits
andersc
12 commits
polarislys
2 commits
