Skip to content

Pull requests: Luce-Org/lucebox-hub

New pull request New
28 Open 132 Closed
28 Open 132 Closed
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
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

feat(server): Add C++ HTTP server
#205 opened May 17, 2026 by howard0su Contributor • Draft
Add Docker prebuilds: cuda12 + cuda13 variants
#198 opened May 15, 2026 by easel Contributor • Draft
4 tasks
fix(dflash): read draft dims from config.json, don't inherit from target
#195 opened May 14, 2026 by easel Contributor • Draft
4 of 5 tasks
feat(gemma4): feature-complete backend with DFlash + MTP + sparse-FA decode (supersedes PR #175 skeleton)
#193 opened May 14, 2026 by dusterbloom Contributor • Draft
feat(dflash): add /props introspection endpoint
#190 opened May 13, 2026 by easel Contributor • Draft
1 of 2 tasks
5
chore(workspace): introduce uv workspace for dflash, megakernel, pflash
#189 opened May 13, 2026 by easel Contributor • Draft
5 of 9 tasks
4
feat(gemma4): target-graph MTP integration (h_prev capture + asymmetric KV)
#183 opened May 13, 2026 by dusterbloom Contributor Loading…
5
feat(gemma4): add mtp loader and step graph
#182 opened May 13, 2026 by dusterbloom Contributor Loading…
6
feat(gemma4): add dflash draft runtime
#181 opened May 13, 2026 by dusterbloom Contributor Loading…
5
feat(gemma4): add draft loader and quantization support
#180 opened May 13, 2026 by dusterbloom Contributor Loading…
9
fix(gemma4): add long-context KV correctness
#177 opened May 13, 2026 by dusterbloom Contributor Loading…
5
docs(dflash): document small-vram cuda vmm guidance
#174 opened May 13, 2026 by dusterbloom Contributor Loading…
4
feat(dflash): add csv token output utility
#173 opened May 13, 2026 by dusterbloom Contributor Loading…
3
feat: Slow-Fast inference support
#163 opened May 13, 2026 by howard0su Contributor Loading…
@davide221
3
feat(dflash): linear native MTP integrated decode CLI (stacked on #153)
#154 opened May 11, 2026 by javierpazo Contributor Loading…
2
feat(dflash): native Qwen3.6 MTP (NextN) runtime + contract test
#153 opened May 11, 2026 by javierpazo Contributor Loading…
3
Add Gemma 4 RTX 4090 backend helpers
#152 opened May 11, 2026 by adybag14-cyber Loading…
@dusterbloom
14
feat(dflash): accept FP16 safetensors drafter alongside BF16
#142 opened May 9, 2026 by javierpazo Contributor Loading…
chore(dflash): enforce sm_89 user override and keep BSA enabled
#137 opened May 9, 2026 by javierpazo Contributor Loading…
4
feat(dflash): native multi-request scheduler with batched target step
#135 opened May 9, 2026 by javierpazo Contributor Loading…
2
Gemma4 support: pFlash + DFlash + chunked prefill, daemon mode, server routing
#131 opened May 8, 2026 by dusterbloom Contributor Loading…
5 of 6 tasks
44
Qwen3.5 MoE support
#120 opened May 7, 2026 by howard0su Contributor Loading…
7
feat(dflash): support Qwen3.6-27B-DFlash draft (SWA layers) — 106 t/s on RTX 4090
#94 opened May 4, 2026 by Quitetall Contributor Loading…
7
feat(pflash): compress role=tool messages in place for agent transcripts
#75 opened May 1, 2026 by easel Contributor • Draft
3 of 6 tasks
1
perf(pflash): add SM75 target-resident TTFT path
#72 opened May 1, 2026 by weicj Contributor Loading…
7
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.