Skip to content

Pull requests: InfiniTensor/InfiniLM

New pull request New
31 Open 179 Closed
31 Open 179 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

feat: support chunkprefill and prefill cuda graph
#371 opened May 12, 2026 by Simon12345777 Loading…
48 tasks
1
issue/349 - Support GLM4 model
#370 opened May 12, 2026 by rubik-hua Loading…
14
refactor: use processor in infer backup
#368 opened May 12, 2026 by wooway777 Collaborator Loading…
29 of 48 tasks
1
refactor: unify linear/quantization architecture and remove deprecate…
#366 opened May 12, 2026 by qinyiqun Contributor Loading…
38 of 48 tasks
11
feat: add prefix hashing for mm_data
#364 opened May 11, 2026 by PanZezhong1725 Collaborator Loading…
1 of 48 tasks
1
issue/350 - add ChatGLM causal LM model support
#353 opened May 7, 2026 by JoeZhang-0x000 Loading…
1
2
issue/349 - add GLM4 causal LM model support
#352 opened May 7, 2026 by JoeZhang-0x000 Loading…
1
5
issue/348 - add Baichuan causal LM model support
#351 opened May 7, 2026 by JoeZhang-0x000 Loading…
1
9
refactor: inline InfiniCore into InfiniLM, switch xmake -> CMake
#324 opened Apr 25, 2026 by zhangyue207 Collaborator • Draft
6 tasks
2
issue/296 - feat: add Worker and ModelRunner for PD disaggregation
#304 opened Apr 15, 2026 by spike-zhu Collaborator Loading…
3
issue/294: minicpm-sala model
#295 opened Apr 8, 2026 by Ceng23333 Contributor Loading…
57
【比赛2025秋】T2-1-3
#268 opened Mar 16, 2026 by PanZezhong1725 Collaborator • Draft
enable FA and fix total_kv_lengths check in infer_engine.
#256 opened Mar 6, 2026 by gongchensu Collaborator Loading…
Issue/224：add warmup before InfiniLM generation，and use muDNN silu_and_mul to replace elementwise swiglu in moore gpu
#225 opened Feb 11, 2026 by spike-zhu Collaborator Loading…
@spike-zhu
1
feat: add operator fusion support with dynamic scheduling
#212 opened Jan 30, 2026 by hootandy321 Loading…
Kv compression 0.2.0
#201 opened Jan 23, 2026 by Ringssss Loading…
LLaDA实现
#197 opened Jan 22, 2026 by MoringLotus Contributor Loading…
issue/143 支持计算图预先编译
#192 opened Jan 19, 2026 by PanZezhong1725 Collaborator Loading…
[2025秋季][T-2-1-1] https://github.com/zincjay
#185 opened Jan 12, 2026 by zincjay Loading…
[2025秋季][2-2-3 MLA 模块]feat: implement Absorb mode optimization
#182 opened Jan 12, 2026 by goog00 Loading…
1
[2025秋季][T2-2-1] lviy
#181 opened Jan 11, 2026 by lviy Loading…
[2025秋季][2-1-4] CearX
#179 opened Jan 11, 2026 by CearX Loading…
1
issue/175: 增加QY机器测试example/jiuge.py
#176 opened Jan 6, 2026 by xgqdut2016 Contributor Loading…
1
5
issue/155: 服务端支持repetition_penalty
#164 opened Dec 25, 2025 by Ceng23333 Contributor Loading…
Issue/136 - 使用add_rms_norm融合算子 enhancement New feature or request
#162 opened Dec 25, 2025 by gongchensu Collaborator Loading…
@gongchensu
ProTip! Add no:assignee to see everything that’s not assigned.