Skip to content

Pull requests: sgl-project/SpecForge

New pull request New
78 Open 455 Closed
78 Open 455 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 continuous ingress to disaggregated producers
#712 opened Jul 20, 2026 by maocheng23 Collaborator • Draft
1
Expand DSpark target support and training scalability
#710 opened Jul 19, 2026 by Boreas618 • Draft
3 of 5 tasks
5
[Feature] Support generate hidden states and vocab_mapping at the same time.
#708 opened Jul 18, 2026 by jiapingW Collaborator Loading…
3 tasks
4
feat(runtime): add heterogeneous one-producer multi-consumer DFlash fanout
#707 opened Jul 18, 2026 by heiheiha798 Loading…
11
feat: --trim-loss-positions (compute teacher/logits/loss only at supe…
#705 opened Jul 17, 2026 by julyanghar Loading…
4 tasks done
10
feat: support offline DFlash-family training
#704 opened Jul 17, 2026 by maocheng23 Collaborator Loading…
4 tasks done
1
fix: rebuild non-persistent rotary buffers after from_pretrained
#703 opened Jul 17, 2026 by julyanghar Loading…
2 tasks done
7
fix(draft): read RoPE parameters from Transformers v5 configs
#702 opened Jul 17, 2026 by wiketool Contributor Loading…
2 tasks done
2
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
rocm: lazy-import yunchang so SpecForge imports on ROCm (foundation)
#698 opened Jul 17, 2026 by zhentaocc • Draft
2 of 3 tasks
3
fix(config): drop redundant qwen3-8b-dta config and example
#697 opened Jul 17, 2026 by curnane-lab Contributor Loading…
2 of 6 tasks
1
1
[WIP] Add EDSD: Entropy-Driven Design for Faster Speculative Decoding
#696 opened Jul 16, 2026 by KerwinKai Contributor • Draft
6 tasks
6
feat(training): single-GPU online-mode memory options
#671 opened Jul 12, 2026 by notwitcheer Loading…
8
feat(training): --vocab-mapping-path to pin the vocab mapping across resumes
#670 opened Jul 12, 2026 by notwitcheer Loading…
4
feat(training): gradient checkpointing for the TTT unroll (--draft-gradient-checkpointing)
#669 opened Jul 12, 2026 by notwitcheer Loading…
1
fix(data): pass per-sample tools list for preformatted batches
#668 opened Jul 10, 2026 by curnane-lab Contributor Loading…
1 of 6 tasks
1
feat: add mtp support
#667 opened Jul 9, 2026 by curnane-lab Contributor Loading…
4 of 6 tasks
3
feat(target_utils): auto-detect embed/lm_head keys for LLM and VLM checkpoints
#666 opened Jul 9, 2026 by curnane-lab Contributor Loading…
6 tasks
4
Fix DFlash sglang target backend for sglang 0.5.13+ scheduler/batch API
#664 opened Jul 8, 2026 by violet73 Loading…
6 tasks
3
fix(train_dflash): atomic per-file checkpoint writes + _SUCCESS-gated resume
#659 opened Jul 7, 2026 by jessiewei7 Contributor Loading…
3
[Modeling] DFlash MLA (DeepSeek) draft + rebase MLA eagle3 onto the #645 stack
#651 opened Jul 5, 2026 by maocheng23 Collaborator • Draft
8
[Online track] O1.3 — live SGLang-server capture (reforward transport)
#641 opened Jul 2, 2026 by maocheng23 Collaborator • Draft
2
[Modeling] MLA (DeepSeek) Eagle3 draft architecture
#640 opened Jul 2, 2026 by maocheng23 Collaborator • Draft
1
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.