Skip to content

Pull requests: lablup/mlxcel

Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort

Pull requests list

perf(cuda): extend sdpa_vector decode kernels to head_dim 256/288 via MLX overlay area:inference Generation, sampling, decoding (incl. speculative, DRY) priority:medium Medium priority status:done Completed type:performance Performance improvements
#681 opened Jul 6, 2026 by inureyes Member Loading…
fix: preserve Qwen3.5 MoE switch projection names area:architecture Architecture and code structure changes priority:medium Medium priority status:investigation Feasibility spike / under investigation type:bug Bug fixes, error corrections, or issue resolutions
#653 opened Jul 4, 2026 by ukint-vs Loading…
ci(deps): bump dtolnay/rust-toolchain from 1.93.1 to 1.100.0 type:chore Maintenance tasks (build, CI, etc.) type:dependency Dependency updates
#146 opened Jun 1, 2026 by dependabot Bot Loading… 0.4
ProTip! Mix and match filters to narrow down what you’re looking for.