-
Notifications
You must be signed in to change notification settings - Fork 122
Pull requests: InfiniTensor/InfiniCore
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
issue/1393 - nsa paged attention and nsa compress paged cache for metax
#1394
opened Jul 13, 2026 by
Lfan-ke
Loading…
[codex] Enable Kunlun Qwen2.5 inference support
#1369
opened Jul 6, 2026 by
zhangyue207
Collaborator
•
Draft
perf(metax): vectorize elementwise kernel for contiguous aligned tensors
#1353
opened Jun 30, 2026 by
LindseyMei
Loading…
issue/1319: NVIDIA机器添加moe_wna16_marlin_gemm
#1334
opened Jun 24, 2026 by
xgqdut2016
Collaborator
Loading…
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…
Previous Next
ProTip!
Updated in the last three days: updated:>2026-07-11.