Open Issues Need Help
View All on GitHub good first issue status:ready type:bug priority:low area:models
lablup/mlxcel
134
High-performance LLM/VLM inference runtime and server for Apple Silicon / CUDA devices
Rust
fix(tests): fused MoE GeGLU parity threshold is tighter than the gather_qmm reference's own jitter about 3 hours ago
good first issue status:ready type:test priority:medium area:core
lablup/mlxcel
134
High-performance LLM/VLM inference runtime and server for Apple Silicon / CUDA devices
Rust
bug: Gemma 4 server reasoning_content retains leading 'thought' prefix from the channel marker about 3 hours ago
good first issue type:bug priority:low
lablup/mlxcel
134
High-performance LLM/VLM inference runtime and server for Apple Silicon / CUDA devices
Rust
feat: need a logo about 1 month ago
help wanted type:enhancement priority:medium area:docs
lablup/mlxcel
134
High-performance LLM/VLM inference runtime and server for Apple Silicon / CUDA devices
Rust