Skip to content

Pull requests: ml-explore/mlx-swift-lm

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

add kvScheme parameter for extensible KV cache compression
#230 opened Apr 21, 2026 by TheTom Loading…
4 tasks done
fix segsum dtype promotion -- 2x memory waste on hybrid SSM models
#229 opened Apr 21, 2026 by TheTom Loading…
4 tasks done
fix Gemma 4 MoE router -- softmax order + fuse norm dispatches
#228 opened Apr 21, 2026 by TheTom Loading…
4 tasks done
add FusedGateUpSwitchGLU -- single fused gate_up_proj for MoE models
#227 opened Apr 21, 2026 by TheTom Loading…
4 tasks done
pipeline prefill chunks with asyncEval -- 10x on GDN models
#225 opened Apr 20, 2026 by TheTom Loading…
2 of 4 tasks
fix gated delta state precision -- fp32 state to match Python
#224 opened Apr 20, 2026 by TheTom Loading…
4 tasks done
Fix EmbeddingGemma init-order crash + dense head hidden size
#223 opened Apr 20, 2026 by 0xweb3r Loading…
2 of 3 tasks
Gemma 3/4 tool calling support
#215 opened Apr 15, 2026 by BRVWL Loading…
Add Gemma 3n E4B audio encoder (Conformer) support
#194 opened Apr 7, 2026 by vahsaechao Loading…
3 of 4 tasks
Adopt GemmaFunctionParser to accomodate Gemma4 tool calls. swift-format Swift format failure in CI
#183 opened Apr 4, 2026 by viktike Loading…
2 of 4 tasks
Fix inaccuracies in (and possibly remove) "skills"
#175 opened Apr 1, 2026 by DePasqualeOrg Contributor Loading…
Handle stringified JSON tool call arguments swift-format Swift format failure in CI
#172 opened Mar 30, 2026 by kuosuko Loading…
fix: flatten prompt in TokenRing.loadPrompt to handle 2D inputs
#170 opened Mar 29, 2026 by spokvulcan Contributor Loading…
2 tasks done
Pass tools schema to ToolCallProcessor for type-aware parsing
#167 opened Mar 28, 2026 by alankessler Contributor Loading…
feat: add ParoQuant (pairwise rotation quantization) support
#164 opened Mar 27, 2026 by spokvulcan Contributor Loading…
4 tasks done
Add TurboQuant KV cache backend swift-format Swift format failure in CI
#160 opened Mar 25, 2026 by timonharz Loading…
Fix Qwen35 VLM crash on text-only inference
#149 opened Mar 15, 2026 by dirvine Loading…
Add parser for GPT-OSS Harmony tool call format
#146 opened Mar 13, 2026 by aleroot Contributor Loading…
3 of 4 tasks
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.