Skip to content

Pull requests: sgl-project/SpecForge

New pull request New
37 Open 317 Closed
37 Open 317 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

fix: move input_ids to CPU before calling MRotaryEmbedding.get_rope_index
#506 opened Mar 18, 2026 by Mandy3311 Loading…
1
DFlash VLM training support with SGLang backend
#505 opened Mar 17, 2026 by Mandy3311 Loading…
5
fixed vlm ci error
#504 opened Mar 17, 2026 by FrankLeeeee Loading…
6 tasks
3
[Feature] Support tool-use parse and reasoning content.
#503 opened Mar 17, 2026 by jiapingW Loading…
4 tasks
3
fix: add default scaling_type handling
#502 opened Mar 16, 2026 by moehanabi Loading…
1 of 6 tasks
7
Fix: support preformatted text datasets in train_eagle3.py (avoid forcing conversations generator)
#498 opened Mar 9, 2026 by Seun-Ajayi Loading…
6 tasks
4
[Feature] Support DFlash Speculative Decoding Training for Qwen3.5 Models
#495 opened Mar 7, 2026 by EanWang211123 Loading…
6 tasks
1
feat: add Qwen3-Coder-Next EAGLE3 draft config
#494 opened Mar 6, 2026 by lujangus Loading…
2 tasks
3
feat: add GLM-4.7-Flash EAGLE3 training support
#493 opened Mar 6, 2026 by lujangus Loading…
3 tasks
8
Add LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding
#492 opened Mar 6, 2026 by MrShevan Loading…
4 tasks done
8
Fix OOM from glibc malloc arena retention during large model training
#491 opened Mar 4, 2026 by yifjiang • Draft
4 tasks
1
Fix eval dataset race condition in multi-node DP training
#490 opened Mar 4, 2026 by yifjiang • Draft
3 tasks
1
Fix multi-node DP training crash from FlashInfer CUDA IPC handles
#489 opened Mar 4, 2026 by yifjiang Loading…
3 tasks done
2
fix: correct always-true condition in HarmonyParser causing duplicate system prompts
#484 opened Mar 2, 2026 by Bias92 Loading…
1
fix: use processor.tokenizer for apply_chat_template in VLM preprocessing
#480 opened Mar 2, 2026 by Bias92 Loading…
2 tasks
1
4
add DFLASH block mask support for SDPA
#477 opened Mar 2, 2026 by wenqf11 Loading…
6 tasks
4
Support Kimi-K2.5 EAGLE3
#476 opened Mar 2, 2026 by UranusSeven • Draft
6 tasks
6
Add Qwen3-VL training adaptation for DFlash
#475 opened Feb 28, 2026 by gq112 Loading…
6 tasks done
1
(feat)Draft model supports Qwen3 MoE
#468 opened Feb 13, 2026 by sadasdasdasdasasd Loading…
1 of 6 tasks
1
add resume for dflash training script
#460 opened Feb 4, 2026 by tianhaoz95 Loading…
1 of 6 tasks
3
feat: add MiniCPM-V-4 VLM support for EAGLE3 training
#451 opened Jan 26, 2026 by Lollipop Loading…
4
dLLM(Dflash) Offline Training Support
#445 opened Jan 21, 2026 by Ximingwang-09 Loading…
6 tasks
4
support pixels range at prepare_hidden_states stage
#438 opened Jan 19, 2026 by justadogistaken Loading…
6 tasks
4
[Bug Fix] add requirements and add tensorboard dependency
#433 opened Jan 18, 2026 by jiapingW Loading…
5 tasks
13
Add Qwen3VL Eagle3 Training Support
#431 opened Jan 18, 2026 by ardenma Loading…
6 tasks
21
ProTip! Filter pull requests by the default branch with base:main.