a694e718e8
[feat](sycl): add opt-in Panther Lake XMX expert backend ( #2250 )
2026-10-19 18:38:25 +08:00
040a4980ec
[feat](kt-kernel): Ascend NPU backend for single-card DeepSeek-V4-Flash offload ( #2157 )
2026-09-01 20:10:24 +08:00
517e7a4368
fix(build): keep AVX2 wheel free of AVX512 flags ( #2164 )
2026-08-18 17:28:00 +08:00
e80614fc2d
[feat](kt-sft): Activation reuse & Int8 kernel refactor & native block-FP8 LoRA SFT ( #2141 )
...
* feat(sft): support distributed activation reuse policies
* feat(sft): add frozen-base INT8 LoRA training
* fix(sft): make INT8 expert LoRA rank-zero authoritative
* fix(sft): preserve DeepSeek router LoRA routing
* feat(sft): enable persistent INT8 LoRA training
* perf(sft): accelerate INT8 VNNI with oneDNN BRGEMM
* perf(int8): fuse oneDNN compensation into backward repack
* [feat]: support BF16 expert LoRA training
* [fix]: honor forwarded activation policy in SFT workers
* feat(sft): add native block-FP8 routed expert LoRA
* feat(sft): expose explicit expert placeholder ownership
* fix(sft): publish fused adapter artifacts atomically
* feat(sft): own artifact and adapter lifecycle contracts
* fix(sft): harden artifact and rank-local contracts
* fix(sft): auto-adapt owner before adapter restore
* style(sft): keep lifecycle comments concise
* fix(sft): require fused adapter manifests
* test(sft): use spawn for distributed workers
* fix(sft): preserve runtime checkpoint metadata
* fix(sft): validate wrapped runtime configuration
* fix(sft): preserve expert format provenance
* fix(sft): own routed experts during device dispatch
* test(sft): lock explicit quantization conflict
* fix(cpu): make shared memory buffers lifetime-safe
* release: prepare v0.7.0
2026-08-17 16:25:14 +08:00
0c2912a5e2
[feat] Add SYCL backend for intel iGPU ( #2089 )
...
* [feat](sycl): add sycl backend for igpu
* [feat](sycl): improve prefill
* [feat](sycl): finish and test sycl gptq int4
2026-07-17 16:24:04 +08:00
7641f5445d
[feat] : Add MACA backend support for kt-kernel and fix CPU MoE tests ( #2044 )
...
* Add MACA backend support for kt-kernel
* Add MACA event API mappings
* Fix AMX build flags and CPU MoE tests
---------
Co-authored-by: <Engle_Chaveztih@sociologist.com >
2026-06-16 16:49:06 +08:00
85308615b9
[build] prepare v0.6.1 SFT wheel packaging on main ( #1945 )
...
* [build]: prepare 0.6.1 SFT wheel packaging on main
* [build]: finalize py311+ wheel packaging defaults
2026-04-24 12:08:38 +08:00
db9326302b
chore: bump version to 0.5.3 ( #1909 )
2026-04-01 18:58:48 +08:00
7a9daf0cd4
[feat](kt-kernel): support avx2 only inference for bf16 fp8 and gptq int4 ( #1892 )
...
* feat: support avx2 bf16 fp8 inference
* feat: support avx2 gptq int4 inference
* fix: numeric issues in fp8 dequant
* Tutorial avx2 (#1900 )
* fix: prevent injecting -DLLAMA_AVX512=ON on AVX2-only machines
* docs: add AVX2 tutorial for running KTransformers on AVX2-only CPUs
* Tutorial avx2 (#1901 )
* fix: prevent injecting -DLLAMA_AVX512=ON on AVX2-only machines
* docs: add AVX2 tutorial for running KTransformers on AVX2-only CPUs
* docs: update README.md
---------
Co-authored-by: Benjamin F <159887351+yyj6666667@users.noreply.github.com >
2026-03-27 14:45:02 +08:00
edc48aba37
[fix]: fix wrapper import issue ( #1819 )
2026-01-28 16:31:56 +08:00
9adc91714f
Remove kt-kernel-cuda, kt-kernel uses the version with cuda ( #1769 )
2025-12-30 10:23:58 +08:00
4b235cdaa4
fix cuda wheel build ( #1766 )
2025-12-29 12:42:06 +08:00
559a3ad4ac
fix pypi cuda install ( #1763 )
2025-12-29 11:19:43 +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
d8046e1bb4
Kt minimax ( #1742 )
...
[feat]: fp8 kernel and kt-cli support
2025-12-24 15:39:44 +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
1f79f6da92
[feat](kt-kernel): Add automatic deployment workflow ( #1719 )
2025-12-16 15:20:06 +08:00
c65febe05c
[feat]: Automatically detect whether blis is installed on amd cpus ( #1702 )
2025-12-11 14:25:36 +08:00
0698252484
[fix](kt-kernel): gate RAWINT4 behind AVX512 and avoid AVX2 build break ( #1660 )
2025-12-03 00:43:23 +08:00
1374b98ee5
[feat](moe_kernel): add amd blis support (int8) ( #1600 )
...
* [feat]: init amd adaption
* [feat]: add blis support
* [fix]: fix setup and moe kernel warpper
* [fix](setup.py): support rebuild with cache and import kt_kernel works
fine
* [feat]: add moe_kernel converter for amd and implement the load
method(haven't tested yet)
* [feat](moe_kernel/moe.hpp): delete unused memory when using save
* [fix](moe_kernel): update PLAIN for pack
* [fix](moe_kernel): rm printf debug
* [fix](moe_kernel): skip gpu experts
* [fix](moe_kernel/moe.hpp): update include memory path
* [feat](moe_kernel/moe.hpp): support expert deferral
* [feat]: finish amd
---------
Co-authored-by: mrhaoxx <mr.haoxx@gmail.com >
2025-11-27 12:08:53 +08:00
d483147307
Fix kt-kernel compile issue ( #1595 )
...
* update install.sh
* fix import issue
* update README
2025-11-11 19:30:27 +08:00
a6bb7651f8
[build]: amd for llamafile right now ( #1594 )
2025-11-11 18:08:03 +08:00
0c15da437f
[feat](cmake & doc): fix bug with cmake arch detect & update doc for sft
2025-11-04 08:46:26 +00:00
f854d03bd7
update kt-kernel
2025-11-03 15:19:52 +08:00
4c5fcf9774
add kt-kernel
2025-10-12 05:13:00 +00:00
callmegaga