1076 commits

This branch

This branch

All branches

Author	SHA1	Message	Date
Wenzhang-Chen	62b7b28a16	fix typo (#1452)	2025-11-10 16:08:04 +08:00
Atream	a9276db254	Merge pull request #1574 from kvcache-ai/Atream-patch-12 ... Change attention backend to 'flashinfer' in launch command	2025-11-08 20:57:03 +08:00
Atream	b67cc4095d	Change attention backend to 'flashinfer' in launch command ... Updated the launch command to include 'flashinfer' as the attention backend.	2025-11-08 20:56:09 +08:00
Peilin Li	0dd4287ff0	Merge pull request #1573 from kvcache-ai/JimmyPeilinLi-patch-4 ... add deepseek-v2 KT-SFT yaml	2025-11-08 17:07:51 +08:00
Peilin Li	388e3eb0c1	add deepseek-v2 KT-SFT yaml	2025-11-08 17:06:13 +08:00
Peilin Li	f4fe137023	Merge pull request #1572 from JimmyPeilinLi/main ... fix: remove py310 as guide	2025-11-08 16:57:10 +08:00
Atream	c56265e541	Merge pull request #1571 from kvcache-ai/Atream-patch-11 ... Simplify launch command by removing unused option	2025-11-08 16:54:49 +08:00
JimmyPeilinLi	1c08a4f0fb	fix: remove py310 as guide	2025-11-08 08:54:32 +00:00
Atream	0651dbda04	Simplify launch command by removing unused option ... Removed the unused '--attention-backend triton' option from the launch command.	2025-11-08 16:54:18 +08:00
Jianwei Dong	8c99148c9c	Merge pull request #1569 from KMSorSMS/main ... [fix]: fix precision of amx int8	2025-11-08 13:38:58 +08:00
KMSorSMS	62d8685699	[fix]: update moe's physical to logical map	2025-11-07 16:29:04 +00:00
KMSorSMS	2641d15383	[fix]: add amx optimization	2025-11-07 15:51:56 +00:00
KMSorSMS	9509220b64	[feat]: Merge branch 'main' of https://github.com/kvcache-ai/ktransformers	2025-11-07 14:56:43 +00:00
KMSorSMS	7b88bb3d39	[fix]: fix precision	2025-11-07 14:56:05 +00:00
Oql	34c71ba8bf	Merge pull request #1568 from kvcache-ai/add_bf16_scripts ... add convert_moe_to_bf16.py	2025-11-07 17:55:38 +08:00
ouqingliang	a18f007d45	add convert_moe_to_bf16.py	2025-11-07 09:53:19 +00:00
Atream	32fab532c6	Merge pull request #1564 from kvcache-ai/Atream-patch-10 ... Fix download link for Kimi-K2-Thinking weights	2025-11-06 19:07:38 +08:00
Atream	d6ee384fe2	Fix download link for Kimi-K2-Thinking weights ... Updated the download link for AMX INT4 quantized weights.	2025-11-06 19:07:15 +08:00
Atream	f3c4dbe181	Merge pull request #1562 from kvcache-ai/kimi-k2-thinking ... Kimi k2 thinking	2025-11-06 18:17:46 +08:00
Atream	86229c852d	Add update for Kimi-K2-Thinking support	2025-11-06 17:56:46 +08:00
Atream	d419024bb4	Add KTransformers SGLang inference documentation ... Add documentation for KTransformers SGLang inference deployment, including installation steps, model download links, server launch instructions, and performance benchmarks.	2025-11-06 17:53:58 +08:00
Peilin Li	1ab570b5ca	Merge pull request #1561 from kvcache-ai/JimmyPeilinLi-patch-3 ... Update SFT Installation Guide for KimiK2	2025-11-06 17:34:33 +08:00
Peilin Li	803e645bc1	Update SFT Installation Guide for KimiK2 ... Added installation instructions and usage examples for KimiK2.	2025-11-06 17:34:21 +08:00
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