-
Notifications
You must be signed in to change notification settings - Fork 70
Pull requests: baidu/vLLM-Kunlun
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[Feature] Add DeepSeek V3.2 W8A8 INT8 model support
#339
opened Apr 24, 2026 by
Lidang-Jiang
Contributor
Loading…
5 tasks done
[Feature][Core] Workaround: Align KVCache precision with GDN forward pass
#336
opened Apr 23, 2026 by
Hyfreadom
Contributor
Loading…
3 tasks done
[Feature] Add Gemma4 model support and refactor RoPE
#334
opened Apr 21, 2026 by
GrootLiu
Loading…
3 tasks done
[Bugfix] Fix missing tie_word_embeddings on Qwen3-VL text_config
#330
opened Apr 20, 2026 by
Lidang-Jiang
Contributor
Loading…
19 tasks done
[Bugfix] Normalize KunlunGraph splitting_ops for piecewise cudagraph
#329
opened Apr 20, 2026 by
Lidang-Jiang
Contributor
Loading…
6 tasks done
[Kernel] Add Eagle next-token prepare op
#325
opened Apr 17, 2026 by
Lidang-Jiang
Contributor
Loading…
6 tasks done
[Kernel] Add MoE bias fused op
#326
opened Apr 17, 2026 by
Lidang-Jiang
Contributor
Loading…
6 tasks done
[Feature] Upgrade vLLM-Kunlun from 0.15.1 to 0.19.0
#315
opened Apr 10, 2026 by
Lidang-Jiang
Contributor
Loading…
4 tasks done
[Kernel]Using workspace manager in quantization
#309
opened Apr 8, 2026 by
Marshall-Ge
Contributor
Loading…
ProTip!
What’s not been updated in a month: updated:<2026-03-25.