-
Notifications
You must be signed in to change notification settings - Fork 54
Pull requests: lablup/mlxcel
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
refactor(webui): adopt every shared @lablup/ui-common component
area:architecture
Architecture and code structure changes
priority:medium
Medium priority
status:review
Under review
type:refactor
Code restructuring without changing functionality
#1924
opened Sep 19, 2026 by
inureyes
Member
Loading…
3 tasks
feat(webui): adopt the ui-common theme system and add a glass theme
area:architecture
Architecture and code structure changes
priority:medium
Medium priority
status:done
Completed
type:enhancement
New features, capabilities, or significant additions
#1923
opened Sep 19, 2026 by
inureyes
Member
Loading…
fix(webui): print the checkpoint's real name as its display name
priority:medium
Medium priority
status:done
Completed
type:bug
Bug fixes, error corrections, or issue resolutions
#1920
opened Sep 19, 2026 by
inureyes
Member
Loading…
11 tasks done
perf(cuda): measure SDPA plan-cache bucketing, recommend against it
area:core
mlxcel-core: MLX FFI, primitives, KV cache, layers
area:inference
Generation, sampling, decoding (incl. speculative, DRY)
platform:linux
Linux (CUDA / packaging) specific
priority:medium
Medium priority
status:review
Under review
type:performance
Performance improvements
#1906
opened Sep 17, 2026 by
inureyes
Member
Loading…
5 of 8 tasks
fix(bench): stop hardcoding the run date and replace GNU-only grep -oP in run_bench.sh
#1899
opened Sep 15, 2026 by
yujung7768903
Loading…
deps(deps): bump the minor-and-patch group across 1 directory with 6 updates
type:dependency
Dependency updates
#1897
opened Sep 15, 2026 by
dependabot
Bot
Loading…
ci(deps): bump actions/setup-node from 5 to 7
type:chore
Maintenance tasks (build, CI, etc.)
type:dependency
Dependency updates
#1879
opened Sep 14, 2026 by
dependabot
Bot
Loading…
test(rocm): promote the FFT probe to a reusable example
area:core
mlxcel-core: MLX FFI, primitives, KV cache, layers
platform:linux
Linux (CUDA / packaging) specific
priority:medium
Medium priority
status:review
Under review
type:test
Test related changes
#1878
opened Sep 13, 2026 by
inureyes
Member
Loading…
test: add reason strings to bare #[ignore] attributes
#1855
opened Sep 12, 2026 by
saitejagirada
Contributor
Loading…
1 task done
feat(vlm): add vision feature caching for LFM2-VL
area:models
Model architectures, weights, loading, metadata
modeltype:vlm
Vision-language model
priority:medium
Medium priority
status:review
Under review
type:enhancement
New features, capabilities, or significant additions
#1135
opened Aug 13, 2026 by
MrFelt0385
Loading…
feat(xla): add Gemma3n audio execution
area:inference
Generation, sampling, decoding (incl. speculative, DRY)
area:models
Model architectures, weights, loading, metadata
priority:low
Low priority
status:blocked
Blocked by dependencies or other issues
type:enhancement
New features, capabilities, or significant additions
feat(xla): add Qwen3-VL DeepStack vision path
area:inference
Generation, sampling, decoding (incl. speculative, DRY)
area:models
Model architectures, weights, loading, metadata
priority:low
Low priority
status:review
Under review
type:enhancement
New features, capabilities, or significant additions
feat: add Qwen2.5-VL OpenXLA vision path
area:inference
Generation, sampling, decoding (incl. speculative, DRY)
area:models
Model architectures, weights, loading, metadata
priority:low
Low priority
status:review
Under review
type:enhancement
New features, capabilities, or significant additions
feat: add Youtu-VL XLA vision and MLA inference (#872)
area:inference
Generation, sampling, decoding (incl. speculative, DRY)
area:models
Model architectures, weights, loading, metadata
priority:low
Low priority
status:review
Under review
type:enhancement
New features, capabilities, or significant additions
feat(xla): support Molmo sparse additive visual embeddings
area:inference
Generation, sampling, decoding (incl. speculative, DRY)
area:models
Model architectures, weights, loading, metadata
priority:low
Low priority
status:review
Under review
type:enhancement
New features, capabilities, or significant additions
feat: add Gemma3 VLM OpenXLA path (#869)
area:inference
Generation, sampling, decoding (incl. speculative, DRY)
area:models
Model architectures, weights, loading, metadata
priority:medium
Medium priority
status:review
Under review
type:enhancement
New features, capabilities, or significant additions
ProTip!
Filter pull requests by the default branch with base:main.