Skip to content

Pull requests: sgl-project/SpecForge

New pull request New
81 Open 504 Closed
81 Open 504 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

Add configurable GQA and MLA sliding-window draft layers
#767 opened Aug 15, 2026 by maocheng23 Collaborator • Draft
feat: add scalable colocated online training
#766 opened Aug 12, 2026 by maocheng23 Collaborator • Draft
4 of 5 tasks
feat(scripts): build a draft vocabulary mapping without regenerating features
#765 opened Aug 12, 2026 by fg11991 Loading…
feat(dspark): support a pruned draft vocabulary for the DFlash family
#764 opened Aug 12, 2026 by fg11991 Loading…
Add online-live mode: train drafters from production serving traffic
#763 opened Aug 10, 2026 by sherlockwu Collaborator Loading…
docs: add npu tutorial
#762 opened Aug 10, 2026 by curnane-lab Contributor Loading…
2 of 6 tasks
Pypi
#761 opened Aug 10, 2026 by jiapingW Collaborator Loading…
6 tasks
Add config-selectable MLA draft attention
#758 opened Aug 8, 2026 by maocheng23 Collaborator • Draft
feat: add Kimi-K3 DSpark template, draft config, and example run
#748 opened Aug 3, 2026 by Boreas618 Contributor Loading…
2 of 6 tasks
fix: degrade empty anchor sampling to a masked batch to avoid multi-r…
#737 opened Aug 1, 2026 by Boreas618 Contributor Loading…
2 of 6 tasks
2
[Feature] Multimodal (image+text) DFlash training via server-side capture (Qwen3.5)
#730 opened Jul 29, 2026 by curnane-lab Contributor Loading…
3 of 6 tasks
3
feat(dspark): add Ulysses sequence parallel training
#728 opened Jul 28, 2026 by maocheng23 Collaborator • Draft
4 of 5 tasks
2
feat(dspark): add Qwen3.5-4B draft config and managed-local NPU disaggregated recipe
#727 opened Jul 28, 2026 by curnane-lab Contributor Loading…
4 of 6 tasks
1
feat(domino): add Qwen3.5-4B managed-local NPU disaggregated recipe
#726 opened Jul 28, 2026 by curnane-lab Contributor Loading…
1 of 6 tasks
1
feat(dspark): add offline USP training support
#725 opened Jul 28, 2026 by calyoung80 Loading…
2 of 6 tasks
2
Add FSDP-aware hybrid Muon optimizer
#717 opened Jul 22, 2026 by maocheng23 Collaborator • Draft
3 of 6 tasks
1
Fuse Domino cross entropy with Triton
#716 opened Jul 22, 2026 by zou3519 Contributor Loading…
5
Domino/Dflash: avoid blocking syncs
#715 opened Jul 21, 2026 by zou3519 Contributor Loading…
9
feat(runtime): add heterogeneous one-producer multi-consumer DFlash fanout
#707 opened Jul 18, 2026 by heiheiha798 • Draft
13
feat: --trim-loss-positions (compute teacher/logits/loss only at supe…
#705 opened Jul 17, 2026 by julyanghar Contributor Loading…
4 tasks done
15
rocm: Domino support (validated + example)
#701 opened Jul 17, 2026 by zhentaocc • Draft
1 of 2 tasks
1
rocm: DFlash support (validated + example)
#700 opened Jul 17, 2026 by zhentaocc • Draft
2 of 3 tasks
1
rocm: EAGLE3 support (lazy yunchang + graceful fa/usp errors + example)
#699 opened Jul 17, 2026 by zhentaocc • Draft
2 of 3 tasks
1
[WIP] Add EDSD: Entropy-Driven Design for Faster Speculative Decoding
#696 opened Jul 16, 2026 by KerwinKai Contributor • Draft
6 tasks
6
feat: add mtp support
#667 opened Jul 9, 2026 by curnane-lab Contributor Loading…
6 tasks done
9
ProTip! Type g i on any issue or pull request to go back to the issue listing page.