master

huangkaiyao1Enable get_scheduler_metadata benchmark for CPU.

12c82882创建于 17 天前历史提交

文件	最后提交记录	最后更新时间
csrc	Add FlagGems v4.2.0	4 个月前
experimental_ops	Add FlagGems v4.2.0	4 个月前
fused	!151 [FlagGems] Fix norm kernels for large N to avoid LLVM backend crash in test_norm_ops.py From: @gcw_KBBvCc3Q Reviewed-by: @chenzheng1030 See merge request: openeuler/triton-cpu!151	2 个月前
modules	Add FlagGems v4.2.0	4 个月前
ops	Enable get_scheduler_metadata benchmark for CPU.	17 天前
patches	Add FlagGems v4.2.0	4 个月前
runtime	Remove references to ARMPL_DIR	18 天前
testing	Add FlagGems v4.2.0	4 个月前
utils	libentry: fast-path cache and O(1) set lookups to reduce dispatch overhead	2 个月前
__init__.py	Comment out unsupported ops in our fork	3 个月前
config.py	Add FlagGems v4.2.0	4 个月前
logging_utils.py	Add FlagGems v4.2.0	4 个月前