-
Notifications
You must be signed in to change notification settings - Fork 157
Pull requests: Luce-Org/lucebox-hub
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
feat(dflash): quality eval harness + chat_template_kwargs fix
#103
opened May 5, 2026 by
dusterbloom
Contributor
Loading…
3 tasks
perf: fix DDTree gallocr reallocation with fixed-size graph
#101
opened May 4, 2026 by
howard0su
Contributor
Loading…
fix(prefix_cache): bump startup_sync timeout 10s → 120s for sm_120 cold-boot JIT
#100
opened May 4, 2026 by
aamsellem
Loading…
fix(dflash): set consumer Blackwell ggml flag when 12x arch selected
#99
opened May 4, 2026 by
easel
Contributor
Loading…
2 tasks
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…
perf(pflash): add SM75 target-resident TTFT path
#72
opened May 1, 2026 by
weicj
Contributor
Loading…
dflash: split target/draft StepGraphs to fix ggml_gallocr realloc per spec-decode step (issue #55)
#62
opened Apr 29, 2026 by
dusterbloom
Contributor
Loading…
4 of 5 tasks
fix(dflash): auto-detect GPU arch to prevent sm_120a on consumer Blackwell
#48
opened Apr 27, 2026 by
easel
Contributor
Loading…
2 tasks
feat(dflash): MoE 35B-A3B support + DDTree CUDA graph reuse
#39
opened Apr 27, 2026 by
dusterbloom
Contributor
Loading…
4 of 5 tasks
ProTip!
Find all pull requests that aren't related to any open issues with -linked:issue.