Skip to content

Pull requests: InfiniTensor/InfiniCore

New pull request New
102 Open 714 Closed
102 Open 714 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

[2026春季][T2-1-3] goog00
#1390 opened Jul 12, 2026 by goog00 Loading…
[2026春季][T2-1-1] goog00
#1389 opened Jul 12, 2026 by goog00 Loading…
[2026春季][T2-1-3]xuzheng567
#1388 opened Jul 12, 2026 by xuzheng567 Loading…
T2-1-1/T2-1-2: 吃kfc
#1387 opened Jul 11, 2026 by GodKickMyAss Loading…
feat: kv caching op for all platforms
#1385 opened Jul 9, 2026 by wooway777 Collaborator • Draft
feat: add DSV4 Hygon ops
#1374 opened Jul 8, 2026 by wooway777 Collaborator • Draft
feat: patch test for kunlunxin
#1371 opened Jul 7, 2026 by wooway777 Collaborator Loading…
[codex] Enable Kunlun Qwen2.5 inference support
#1369 opened Jul 6, 2026 by zhangyue207 Collaborator • Draft
feat: support lp_norm operator on metax
#1359 opened Jul 1, 2026 by LindseyMei Loading…
2
perf(metax): vectorize elementwise kernel for contiguous aligned tensors
#1353 opened Jun 30, 2026 by LindseyMei Loading…
1
feat: add standalone infinirt graph bridge
#1351 opened Jun 30, 2026 by gongchensu Collaborator Loading…
@gongchensu
feat: support softmax operator on metax
#1347 opened Jun 29, 2026 by LindseyMei Loading…
1
feat: support quickgelu operator on metax
#1343 opened Jun 26, 2026 by LindseyMei Loading…
feat: support sigmoid operator on metax
#1338 opened Jun 25, 2026 by LindseyMei Loading…
1
issue/1319: NVIDIA机器添加moe_wna16_marlin_gemm
#1334 opened Jun 24, 2026 by xgqdut2016 Collaborator Loading…
[2026春季][ T1-1-8] zili2004
#1326 opened Jun 21, 2026 by zili2004 Loading…
1
[2026春季][ T1-1-10] zili2004
#1325 opened Jun 21, 2026 by zili2004 Loading…
1
[2026春季][ T1-1-9] zili2004
#1323 opened Jun 21, 2026 by zili2004 Loading…
1
[2026春季][ T1-1-7] zili2004
#1322 opened Jun 21, 2026 by zili2004 Loading…
1
Issue/1192 clean：NVIDIA平台增加awq,gptq repack算子
#1299 opened Jun 16, 2026 by xgqdut2016 Collaborator Loading…
issue/1283 - optimize cambricon paged caching
#1286 opened Jun 15, 2026 by wooway777 Collaborator Loading…
1
issue/1271 - update tensor from torch
#1274 opened Jun 12, 2026 by wooway777 Collaborator Loading…
1
issue/1270 - optimize test framework
#1272 opened Jun 12, 2026 by wooway777 Collaborator Loading…
1
issue/1259 - patch kunlun gemm bf16
#1261 opened Jun 12, 2026 by wooway777 Collaborator • Draft
1
issue/1252 - support paged fp32 on Nvidia, Metax, Moore and Iluvatar
#1253 opened Jun 12, 2026 by wooway777 Collaborator Loading…
1
ProTip! Mix and match filters to narrow down what you’re looking for.