1253 commits

This branch

This branch

All branches

Author	SHA1	Message	Date
Peilin Li	3e0f72f7ee	Merge pull request #1560 from kvcache-ai/JimmyPeilinLi-patch-2 ... installation guide for KT+SFT(LoRA) in KimiK2 model	2025-11-06 17:32:55 +08:00
Peilin Li	747dc0596c	Merge pull request #1559 from kvcache-ai/JimmyPeilinLi-patch-1 ... add the convert from fp8 to bf16 for Kimi-K2 model	2025-11-06 17:32:20 +08:00
Peilin Li	d7ec838d5a	installation guide for KT+SFT(LoRA) in KimiK2 model	2025-11-06 17:27:42 +08:00
Peilin Li	d939e56646	add the convert from fp8 to bf16 for Kimi-K2 model	2025-11-06 17:20:28 +08:00
Jianwei Dong	473468da19	Merge pull request #1558 from kvcache-ai/update-readme-sft ... update readme.md	2025-11-05 23:31:38 +08:00
ovowei	44e47ad75a	update readme.md	2025-11-05 23:30:58 +08:00
Jianwei Dong	fc599ed178	Merge pull request #1557 from kvcache-ai/update-readme-sft ... update readme.md	2025-11-05 23:30:27 +08:00
ovowei	00f038e763	update readme.md	2025-11-05 23:29:59 +08:00
Jianwei Dong	62fdf1507e	Merge pull request #1554 from KMSorSMS/main ... [build](cmake): fix error if blis no found for amd	2025-11-05 23:24:22 +08:00
KMSorSMS	85abac27c8	[build](cmake): fix target include bug	2025-11-05 08:04:12 +00:00
KMSorSMS	4b700a816a	[feat]: Merge branch 'main' of https://github.com/kvcache-ai/ktransformers	2025-11-05 05:06:43 +00:00
KMSorSMS	b70c44a959	[build](cmake): not error if blis not found	2025-11-05 05:05:39 +00:00
ZiWei Yuan	350b5c7929	Merge pull request #1552 from kvcache-ai/JimmyPeilinLi-patch-2 ... Revise GPU/CPU memory footprint information	2025-11-05 12:23:49 +08:00
ZiWei Yuan	8192cc4166	Merge pull request #1551 from kvcache-ai/JimmyPeilinLi-patch-1 ... Revise GPU/CPU memory footprint information	2025-11-05 12:23:28 +08:00
ZiWei Yuan	95814c72b2	Merge pull request #1550 from kvcache-ai/lpl-dev-1 ... Update installation instructions	2025-11-05 12:22:59 +08:00
ZiWei Yuan	f6644c9fbd	Merge pull request #1549 from kvcache-ai/lpl-dev ... Update installation instructions	2025-11-05 12:22:37 +08:00
Peilin Li	ebae8ea817	Revise GPU/CPU memory footprint information ... Updated memory footprint details for DeepSeek models.	2025-11-05 12:12:10 +08:00
Peilin Li	6721f8765d	Revise GPU/CPU memory footprint information ... Updated memory footprint details for DeepSeek models.	2025-11-05 12:11:19 +08:00
Peilin Li	4f9940700e	Update installation instructions	2025-11-04 23:06:05 +08:00
Peilin Li	fe556bba34	Update installation instructions	2025-11-04 23:03:36 +08:00
ZiWei Yuan	501b114863	Merge pull request #1548 from KMSorSMS/main ... [feat](cmake & doc): fix bug with cmake arch detect & update doc for sft	2025-11-04 19:52:05 +08:00
KMSorSMS	0c15da437f	[feat](cmake & doc): fix bug with cmake arch detect & update doc for sft	2025-11-04 08:46:26 +00:00
ZiWei Yuan	e40ba6dfae	Merge pull request #1547 from JimmyPeilinLi/KSFT ... [Feature] SFT for KT	2025-11-04 14:37:38 +08:00
JimmyPeilinLi	7b6ccc3f57	add the docs and update README for KSFT	2025-11-04 05:51:48 +00:00
JimmyPeilinLi	4421d48108	[Feature] Add SFT feature for KT	2025-11-04 04:24:30 +00:00
Atream	b09e99fd87	Merge pull request #1545 from kvcache-ai/develop-cht ... update kt-kernel: support Expert Deferral mechanism	2025-11-04 10:25:31 +08:00
chenht2022	6fe30af50d	Merge branch 'main' into develop-cht	2025-11-03 14:35:44 +00:00
Jianwei Dong	9f2cb4787c	Merge pull request #1542 from KMSorSMS/main ... [build]: fix amx cmake build support	2025-11-03 20:01:32 +08:00
Jianwei Dong	0d7482fcc4	Merge pull request #1543 from kvcache-ai/djw-update-kt-kernel-2 ... update kt-kernel	2025-11-03 15:21:19 +08:00
ovowei	f854d03bd7	update kt-kernel	2025-11-03 15:19:52 +08:00
KMSorSMS	b8f099c8b3	[build]: in case of missing, adding two more flags: -mamx-bf16 -mamx-int8s	2025-11-03 04:07:53 +00:00
KMSorSMS	1e85faac77	[fix]: Merge remote-tracking branch 'upstream/main'	2025-11-03 04:00:20 +00:00
KMSorSMS	49a49ade66	[build]: fix amx cmake build support	2025-11-03 03:58:36 +00:00
Jianwei Dong	1a925769d9	Merge pull request #1540 from KMSorSMS/main ... [build]: fix cmake env settings bug	2025-11-03 10:34:08 +08:00
KMSorSMS	164b13adac	[build]: fix cmake env settings bug	2025-11-02 04:49:27 +00:00
chenht2022	dd4377b60b	feat: add deferred expert scheduling support	2025-10-31 08:03:37 +00:00
Jianwei Dong	7b7b72604c	Merge pull request #1538 from kvcache-ai/djw-update-readme ... fix	2025-10-30 10:47:50 +08:00
ovowei	1e17d75bfd	fix	2025-10-30 10:47:05 +08:00
Jianwei Dong	cd508eb625	Merge pull request #1535 from RICHARDNAN/csx-main-fix ... Update DeepseekR1_tutorial_zh_for_Ascend_NPU.md	2025-10-30 10:32:55 +08:00
RICHARDNAN	6085dea039	Update DeepseekR1_V3_tutorial_zh_for_Ascend_NPU.md	2025-10-30 10:05:54 +08:00
RICHARDNAN	536bea29aa	Update DeepseekR1_V3_tutorial_zh_for_Ascend_NPU.md	2025-10-30 10:03:50 +08:00
RICHARDNAN	d96614627d	Update DeepseekR1_V3_tutorial_zh_for_Ascend_NPU.md	2025-10-30 09:53:31 +08:00
RICHARDNAN	2a29a57b7a	Rename tutorial file for DeepseekR1 V3	2025-10-30 09:50:14 +08:00
RICHARDNAN	2716345637	Update tutorial to reflect Deepseek-R1 deployment	2025-10-30 09:48:37 +08:00
RICHARDNAN	6b68fc68d2	Update optimize_config_path for NPU tutorial	2025-10-29 10:47:44 +08:00
RICHARDNAN	bb14f7594e	Revise KTrans benchmark results in tutorial ... Updated benchmark results for KTrans performance.	2025-10-29 09:44:57 +08:00
RICHARDNAN	69af4ddae8	Update DeepseekR1_tutorial_zh_for_Ascend_NPU.md	2025-10-28 22:11:04 +08:00
RICHARDNAN	59a722bf6f	Update doc/zh/DeepseekR1_tutorial_zh_for_Ascend_NPU.md ... Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>	2025-10-28 22:08:27 +08:00
RICHARDNAN	578ed0bfd0	Update doc/zh/DeepseekR1_tutorial_zh_for_Ascend_NPU.md ... Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>	2025-10-28 22:07:48 +08:00
RICHARDNAN	f9028f0315	Update doc/zh/DeepseekR1_tutorial_zh_for_Ascend_NPU.md ... Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>	2025-10-28 22:07:37 +08:00