Skip to content

Pull requests: sgl-project/SpecForge

New pull request New
30 Open 313 Closed
30 Open 313 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 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…
3 tasks
1
fix: include all subpackages in pyproject.toml and remove empty requirements.txt
#483 opened Mar 2, 2026 by Bias92 Loading…
3 tasks
1
1
fix: handle empty/invalid conversations to prevent IndexError in data parsing
#482 opened Mar 2, 2026 by Bias92 Loading…
3 tasks
1
1
fix: disable tokenizers parallelism to prevent dataset map deadlock
#481 opened Mar 2, 2026 by Bias92 Loading…
3 tasks
1
7
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
3
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
Multi-layer Decoder for Llama3 Draft Model enhancement New feature or request
#401 opened Jan 2, 2026 by xiaoxi-s Loading…
4 of 6 tasks
@xiaoxi-s
15
[Clean] Fix warnings and abnormal outputs during training
#393 opened Dec 26, 2025 by lmyybh Loading…
1 of 6 tasks
6
fix data processing + resume training
#390 opened Dec 25, 2025 by Dogacel Loading…
2 of 6 tasks
7
Support check pointing for data generated
#342 opened Dec 1, 2025 by yubofredwang • Draft
6 tasks
[Feature] Add accept length simulator for QwenVL
#279 opened Nov 7, 2025 by Lihui-Gu Loading…
6 tasks
6
Added mistral model support
#208 opened Sep 1, 2025 by ValeGian Loading…
3 of 6 tasks
21
Support Train Eagle-3 By DeepSpeed
#197 opened Sep 1, 2025 by xq25478 Loading…
13
ProTip! Mix and match filters to narrow down what you’re looking for.