Skip to content

Pull requests: InfiniTensor/InfiniCore

New pull request New
86 Open 589 Closed
86 Open 589 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

issue/1180 refactor(nn): decouple RoPE scaling logic with polymorphic interfaces
#1181 opened May 28, 2026 by rubik-hua Loading…
Issue/1177：NVIDIA机器上添加awq_marlin_gemm和gptq_marlin_gemm算子
#1178 opened May 27, 2026 by xgqdut2016 Collaborator Loading…
performance: remove conv algo choosing
#1176 opened May 27, 2026 by PanZezhong1725 Collaborator Loading…
1
feat: implement mha op with flash_attn::mha_fwd
#1174 opened May 26, 2026 by PanZezhong1725 Collaborator Loading…
1
1
doc: update readme
#1172 opened May 26, 2026 by wooway777 Collaborator Loading…
issue/1167 - feat: add flash-attn via MooreThreads/mate for moore gpu
#1168 opened May 21, 2026 by spike-zhu Contributor Loading…
@spike-zhu
4
[2026春季][T1-1-1] mygitljf
#1166 opened May 19, 2026 by mygitljf Loading…
[2026春季][T1-1-1] HyosungSink
#1164 opened May 18, 2026 by HyosungSink • Draft
add operator add to adapt ascend
#1163 opened May 12, 2026 by Jingbo-gao Loading…
issue/1160 - iluvatar fla from zx
#1161 opened May 11, 2026 by wooway777 Collaborator • Draft
1
issue/1148: PagedAttentionPrefill 添加 KV cache 连续性 guard
#1149 opened Apr 30, 2026 by JoeZhang-0x000 Loading…
1
2
issue/1113：NVIDIA机器添加awq_marlin_gemm算子
#1137 opened Apr 21, 2026 by xgqdut2016 Collaborator Loading…
issue/1124: minicpm-sala model
#1125 opened Apr 7, 2026 by Ceng23333 Collaborator Loading…
20
issue/1083: NVIDIA机器添加gptq_marlin_gemm算子
#1110 opened Mar 31, 2026 by xgqdut2016 Collaborator Loading…
1
3
issue/1102: QY和NVIDIA机器添加gptq_gemm算子
#1107 opened Mar 26, 2026 by xgqdut2016 Collaborator Loading…
1
1
issue/1100 Add round and cosh operator integration
#1101 opened Mar 20, 2026 by GordonYang1 Loading…
fa hygon
#1095 opened Mar 20, 2026 by zhangyue207 Collaborator • Draft
Add native nvidia backend for flash attention.
#1060 opened Mar 6, 2026 by gongchensu Collaborator Loading…
fix moore can not compile mccl bf16
#1028 opened Feb 26, 2026 by zichen-kuuga Loading…
Issue/1016 - limiting run.py defaults
#1017 opened Feb 11, 2026 by wooway777 Collaborator Loading…
[2025秋季][T1-1-12] PPPoint-t
#1005 opened Feb 5, 2026 by PPPoint-t Loading…
[2025秋季][T1-1-11] PPPoint-t
#1000 opened Jan 30, 2026 by PPPoint-t Loading…
feat: 添加算子融合调度器模块
#997 opened Jan 30, 2026 by hootandy321 Loading…
Add operator fusion optimization support
#993 opened Jan 29, 2026 by hootandy321 Loading…
1
[2025秋季][T1-1-19] guozhihao-224
#981 opened Jan 23, 2026 by guozhihao-224 Loading…
ProTip! Add no:assignee to see everything that’s not assigned.