1793 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Yanzhi_YI	a07605af50	bugfix: global env	2025-11-17 20:26:53 +08:00
Yanzhi_YI	c18fbd8332	refactor: merge dup code	2025-11-17 19:50:54 +08:00
Yanzhi_YI	a8f4aba8ed	[AIKG][REFACTOR] refactor: verifier adapters	2025-11-17 19:50:53 +08:00
Yanzhi_YI	47b99ff15c	!1256 [AIKG] add glm 4.6 api ... Merge pull request !1256 from Yanzhi_YI/glm	2025-11-17 08:34:37 +00:00
i-robot	0b17bda24e	!1250 [AKG-MLIR] Add initial NPU autotiling support wiring ... Merge pull request !1250 from yuziyu/br_aikg	2025-11-17 08:07:07 +00:00
Yanzhi_YI	742ba51b78	add glm 4.6 api	2025-11-17 14:31:00 +08:00
sasaki	9956b303d0	Add initial NPU autotiling support wiring	2025-11-17 11:34:48 +08:00
i-robot	1410ed2f7a	!1249 【AKG-MLIR】add AkgAutoTilingFuncPass ... Merge pull request !1249 from ombre_mer/br_aikg	2025-11-17 02:28:26 +00:00
ombre_mer	ff54526eb5	add AkgAutoTilingFuncPass	2025-11-16 19:48:21 +08:00
Yanzhi_YI	2b061700f4	!1247 [AIKG] Fix Triton autotune in verify process ... Merge pull request !1247 from dujinye/fix	2025-11-13 06:18:34 +00:00
dujinye	4c1699b922	fix autotune	2025-11-12 23:23:43 +08:00
Yanzhi_YI	5d09b677c0	!1248 update readme: qr code ... Merge pull request !1248 from Yanzhi_YI/logo	2025-11-12 13:33:00 +00:00
Yanzhi_YI	dacc9a2c9c	update readme: qr code	2025-11-12 21:31:06 +08:00
i-robot	af209d4e4f	!1244 FixDtype ... Merge pull request !1244 from 花无懿/br_aikg	2025-11-11 11:05:12 +00:00
花无懿	bf0c4d2fa0	FixDtype	2025-11-11 18:28:07 +08:00
Yanzhi_YI	014783a2a7	!1241 [AIKG] refactor: split triton_ascend/triton_cuda ... Merge pull request !1241 from Yanzhi_YI/backend	2025-11-11 09:07:26 +00:00
Yanzhi_YI	dfb2488aca	bugfix: triton_ascend/cuda usages	2025-11-11 16:26:21 +08:00
Yanzhi_YI	7aa821a83a	refactor: split triton_ascend/triton_cuda	2025-11-11 16:26:20 +08:00
dujinye	998aa49184	triton_cuda docs	2025-11-11 16:26:20 +08:00
Yanzhi_YI	ecadf5ce0d	!1232 [AIKG]add triton_ascend case ... Merge pull request !1232 from hujiahui8/new_benchmark	2025-11-11 08:25:52 +00:00
i-robot	c8b564d758	!1243 FixSubviewShape ... Merge pull request !1243 from 花无懿/br_aikg	2025-11-11 08:06:18 +00:00
花无懿	c18b5957f2	FixSubviewShape	2025-11-11 15:57:58 +08:00
Yanzhi_YI	31ff437b7c	!1242 fix ascedc dsl bug ... Merge pull request !1242 from zhengqishui/br_aikg	2025-11-11 07:52:48 +00:00
hujiahui8	e85649b066	update elemwise_range	2025-11-11 11:09:15 +08:00
zhengqishui	e78477a76c	fix ascedc dsl bug	2025-11-11 10:58:30 +08:00
hujiahui8	0591209f1c	!33 add all-reduce ... Merge pull request !33 from zhuyiyang/reduce	2025-11-11 02:53:58 +00:00
zhengqishui	99d43f2f61	add ascendc dsl and relative docs	2025-11-11 10:53:52 +08:00
zhu_yiyang	1f0fe83c30	add all-reduce	2025-11-11 10:31:28 +08:00
i-robot	6c7ac1802a	!1229 [MLIR] Auto-infer reduce axes ... Merge pull request !1229 from salazar111/br_aikg	2025-11-11 02:15:47 +00:00
salazar111	82316ef6ea	fix: expandshapeop errors and reduce operation handling	2025-11-11 10:04:49 +08:00
Yanzhi_YI	63afce71f5	!1239 add akg sig qr code ... Merge pull request !1239 from Yanzhi_YI/logo	2025-11-10 15:57:22 +00:00
Yanzhi_YI	ee3b7d7b6f	!1240 [AIKG] add more gpu backend ... Merge pull request !1240 from Yanzhi_YI/backend	2025-11-10 15:07:12 +00:00
Yanzhi_YI	fbd26b89eb	!1237 [MLIR] support affine fusion for ascend st ... Merge pull request !1237 from liuchao/affine_ascend	2025-11-10 12:46:58 +00:00
i-robot	35a8e7062a	!1234 [MLIR] Add a version of tiling implementation on the GPU ... Merge pull request !1234 from yuziyu/br_aikg	2025-11-10 12:37:58 +00:00
sasaki	c04939be03	Add a version of tiling implementation on the GPU	2025-11-10 19:56:27 +08:00
Yanzhi_YI	df07a2192c	add akg sig qr code	2025-11-10 19:23:06 +08:00
liuchao	bfe9e4ba8d	support affine fusion for ascend st	2025-11-10 17:57:10 +08:00
i-robot	d2d1394a49	!1235 AffineForVectorize ... Merge pull request !1235 from 花无懿/br_aikg	2025-11-10 03:52:17 +00:00
花无懿	5cc250a543	AffineForVectorize	2025-11-10 10:55:55 +08:00
hujiahui8	58db949be7	remove case	2025-11-08 17:04:54 +08:00
zouwenxiang	82fbc882c1	matmul bench	2025-11-07 19:00:40 +08:00
chenwangyi	aa1fd851b2	add broadcast cases	2025-11-07 19:00:28 +08:00
hujiahui8	51bfe4874c	update docs	2025-11-07 17:49:25 +08:00
zhu_yiyang	55a8b647dc	add reduce-y docs	2025-11-07 17:49:25 +08:00
hujiahui8	560169b848	fix bug	2025-11-07 17:49:25 +08:00
zhu_yiyang	a139e5e0f6	reudce: atomic and weighted_swiglu_bwd	2025-11-07 17:49:24 +08:00
chenwangyi	3845ef2579	add broadcast cases	2025-11-07 17:49:24 +08:00
zhengqishui	2899342ad7	add elemwise triton profile docs and case	2025-11-07 17:49:23 +08:00
zhu_yiyang	dd2b86ae1e	add reduce samples	2025-11-07 17:49:23 +08:00
chenwangyi	bf5326f378	add elemwise impl and docs	2025-11-07 17:49:22 +08:00