978dedee75
[fix]: fix experts-sched-Tutorial.md
2026-01-23 10:04:45 +00:00
bf4c8a690b
Add Native Precision Tutorial, update worker strategy and README.md ( #1807 )
2026-01-23 18:00:13 +08:00
8652346e69
[fix]: doc ( #1805 )
2026-01-23 11:17:08 +08:00
b0f827d2a9
[chore](cuda): explicitly use ele_per_blk var for better readability ( #1784 )
2026-01-23 11:11:08 +08:00
779bf14556
[doc]: add Experts sched tutorial ( #1802 )
...
* Change num gpu experts to gpu expert masks and add eplb statistics
* [feat]: update examples
* [fix]: fix fp8 perchannel
* Delete useless tests
* Delete useless tests
* add experts_sched tutorial
---------
Co-authored-by: ouqingliang <1692110604@qq.com >
2026-01-22 15:40:07 +08:00
a4de664e62
Add AutoDL Tutorial ( #1801 )
2026-01-22 14:52:47 +08:00
d2305538f7
Modify installation steps in Kimi-K2-Thinking-Native.md ( #1800 )
...
Updated installation instructions for sglang repository.
2026-01-21 15:46:21 +08:00
b27de4068b
[fix]: fix exp_avx512 for act_fn ( #1797 )
2026-01-20 11:07:22 +08:00
027832c590
[feat](kt-kernel): CPU-GPU experts sched ( #1796 )
2026-01-16 17:01:15 +08:00
6277da4c2b
support GLM 4.7 ( #1791 )
...
support GLM 4.7
2026-01-13 17:36:25 +08:00
667030d6e6
[kt-kernel]: Fix ignored build configurations in install.sh and CMakeLists.txt ( #1789 )
...
* Correct variable defaults
* Remove CMAKE_BUILD_TYPE setting in CMakeLists
2026-01-12 22:16:19 +08:00
5edc456749
support Native BF16 format MoE. ( #1788 )
...
support Native BF16 format MoE
2026-01-12 14:43:28 +08:00
ddb957596f
Fix moe bug. ( #1783 )
...
* [fix]: fix moe.hpp load from file bug.
* [fix]: fix all moe hpp init bug.
* [fix]: fix moe & awq-moe ug.
2026-01-05 17:02:24 +08:00
dc6394e501
[fix]: fix moe hpp bug. ( #1780 )
...
fix moe hpp init bug.
2026-01-04 19:32:56 +08:00
ad7674a6d5
[ci]: Patch ci ( #1772 )
...
* [docs]: add kt-cli doc and update corresponding website
* [feat]: update issue template
2025-12-31 12:10:20 +08:00
6d2d7cb057
bump to 0.5.0.post1 ( #1771 )
2025-12-30 11:09:54 +08:00
47b1bfcff6
Update release-pypi.yml ( #1770 )
2025-12-30 10:47:28 +08:00
9adc91714f
Remove kt-kernel-cuda, kt-kernel uses the version with cuda ( #1769 )
2025-12-30 10:23:58 +08:00
b096b01fbc
[docs]: add kt-cli doc and update corresponding website ( #1768 )
2025-12-29 23:06:22 +08:00
9539ab91eb
Cli ( #1765 )
...
* [feat]: add custom option for kt run
* [feat]: depth 3
2025-12-29 15:18:42 +08:00
4b235cdaa4
fix cuda wheel build ( #1766 )
2025-12-29 12:42:06 +08:00
7c127d9fd0
Update release-pypi.yml ( #1764 )
2025-12-29 11:48:55 +08:00
559a3ad4ac
fix pypi cuda install ( #1763 )
2025-12-29 11:19:43 +08:00
63796374c1
[docs]: fix and add MiniMax-M2 tutorial images. ( #1752 )
2025-12-25 20:14:35 +08:00
be668074de
Update tutorial links in README.md ( #1749 )
2025-12-25 14:26:10 +08:00
46b0f36980
[feat](kt-kernel): Fix CPU instruction set variants for build & install ( #1746 )
...
* [feat]: Enhance CPU feature detection and support for AVX512 extensions
- Added cmake/DetectCPU.cmake for automatic CPU feature detection.
- Updated CMakeLists.txt to include auto-detection logic for AVX512 features.
- Modified install.sh to include new AVX512_VBMI option for FP8 MoE.
- Enhanced _cpu_detect.py to support progressive matching of CPU variants.
- Created scripts/check_cpu_features.py for manual CPU feature checks.
- Updated setup.py to reflect changes in CPU variant building and environment variables.
* [fix](kt-kernel): Add conditional inclusion of FP8 MoE for AVX512 BF16 support
* [chore](kt-kernel): update project version to 0.5.0 in CMakeLists.txt and version.py
2025-12-24 18:57:45 +08:00
dc5feece8f
[docs]: update doc link ( #1745 )
2025-12-24 18:00:47 +08:00
3315335fb1
[docs]: update docs to kt-kernel & add amd_blis doc ( #1744 )
2025-12-24 17:55:15 +08:00
1d7a476523
[fix]: fix version to 0.5.0 ( #1743 )
2025-12-24 17:33:22 +08:00
d8046e1bb4
Kt minimax ( #1742 )
...
[feat]: fp8 kernel and kt-cli support
2025-12-24 15:39:44 +08:00
e7d277d163
[docs]: refine README for dpo updates ( #1740 )
...
* [docs]: refine dpo tutorial
* [docs]: refine README for dpo updates
* Update doc/en/DPO_tutorial.md
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
* [docs]: update website doc & refine location
---------
Co-authored-by: ErvinXie <ervinxie@foxmail.com >
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: ZiWei Yuan <yzwliam@126.com >
2025-12-24 11:20:08 +08:00
dee1e211d5
[docs]: refine dpo tutorial ( #1739 )
2025-12-22 18:44:24 +08:00
0bce173e3b
[feat]: Release version to 0.4.4 ( #1738 )
2025-12-22 11:20:40 +08:00
16d5d89f50
[docs]: Update Python version options in DPO tutorial ( #1734 )
2025-12-20 13:44:35 +08:00
df998e0f36
[docs]: Add RL-DPO Tutorial ( #1733 )
2025-12-20 12:49:02 +08:00
39449ed1af
update PyPI Install and readme ( #1731 )
2025-12-18 17:21:47 +08:00
3c134359bc
Fix CPU Instruction Set and Installation ( #1729 )
...
* [fix](kt-kernel): fix AVX512 cpu instruction set detection
* [feat](kt-kernel): AVX512 fallback kernel for RAW-INT4
* [fix](kt-kernel): fix setup version issue
* [fix](kt-kernel): update install for custom build
* [docs](kt-kernel): new installation guide for various cpu instruction set
* [fix](kt-kernel): fix _mm512_dpbusd_epi32_compat fallback implmentation
* [style](kt-kernel): clang format
2025-12-18 00:11:57 +08:00
a8667ddb58
[fix](test): fix import kt-kernel ( #1728 )
2025-12-17 19:46:32 +08:00
6fc4080a7d
[fix](kt-kernel): fix typo in moe-tp's forward time-profiling ( #1720 )
...
* [fix](kt-kernel): fix typo in moe-tp's forward time-profiling
* [fix](kt-kernel): fix the experts count in profiling
---------
Co-authored-by: KMSorSMS <yzwliam@126.com >
2025-12-17 12:06:33 +08:00
661e19a8e5
Update release-pypi.yml ( #1726 )
2025-12-16 20:37:20 +08:00
5ba3fb56d1
Update release-pypi.yml ( #1725 )
2025-12-16 20:30:03 +08:00
3126b8deaa
Update release-pypi.yml ( #1724 )
2025-12-16 17:45:29 +08:00
6dcacd9daf
Update release-pypi.yml ( #1723 )
2025-12-16 17:42:28 +08:00
fe8049d3a9
Update release-pypi.yml ( #1722 )
2025-12-16 17:35:29 +08:00
5ff0026fc1
Update release-pypi.yml ( #1721 )
2025-12-16 17:29:29 +08:00
1f79f6da92
[feat](kt-kernel): Add automatic deployment workflow ( #1719 )
2025-12-16 15:20:06 +08:00
f25e58ad69
fix: qwen3-npu bugs; update: add readme-for-qwen3-npu ( #1717 )
...
* fix: qwen3-npu bugs; update: add readme-for-qwen3-npu
* fix: Correct the README description
2025-12-16 14:27:04 +08:00
18fb8fc897
Npu revise benchmark results and prerequisites ( #1716 )
...
* Update DeepseekR1_V3_tutorial_zh_for_Ascend_NPU.md
* Update DeepseekR1_V3_tutorial_zh_for_Ascend_NPU.md
* Revise Ascend NPU tutorial for Docker deployment
Updated the tutorial for deploying the Ascend NPU, changing sections from 'Conda部署' to '镜像部署' and providing specific commands for Docker container setup and Python environment installation.
* Update DeepseekR1 tutorial for Ascend NPU
* Update DeepseekR1_V3_tutorial_zh_for_Ascend_NPU.md
* Update W8A8 weight link in tutorial
* Update doc/zh/DeepseekR1_V3_tutorial_zh_for_Ascend_NPU.md
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
* Refactor Docker command and update package manager
Updated Docker run command to simplify device specifications and corrected package manager command from 'apt' to 'yum'.
* Update DeepseekR1_V3_tutorial_zh_for_Ascend_NPU.md
* Revise benchmark results and prerequisites
Updated performance results and hardware specifications.
* Update doc/zh/DeepseekR1_V3_tutorial_zh_for_Ascend_NPU.md
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
---------
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-12-16 14:26:44 +08:00
34230eaf44
[docs]: Fix image link in README.md ( #1718 )
...
Updated image link to use raw GitHub URL for better accessibility.
2025-12-15 17:10:15 +08:00
008de19e16
[fix](kt-kernel): drop the weights held in Python for loading weights operation in C++ ( #1695 )
2025-12-12 11:42:33 +08:00
ouqingliang