13 commits

Author	SHA1	Message	Date
mrhaoxx	a98d544833	merge: integrate origin/main into sft branch ... Resolved 6 conflicts: - CMakeLists.txt: keep cpptrace + debug flag, accept flexible build type - worker_pool.cpp: keep SFT profiling + main's block=1 spin fix - ext_bindings.cpp: keep both SFT MOE bindings and AVX2/BF16/FP8 bindings - common.hpp: keep gpu_experts_mask + SFT backward weight fields - __init__.py: export both generate_gpu_experts_masks and AMXSFTMoEWrapper - experts.py: gpu_experts_mask for inference, num_gpu_experts for SFT, new methods	2026-04-08 23:19:28 +08:00
mrhaoxx	f36699affd	feat(sft): AMX MoE SFT backend with LoRA support ... Complete SFT (Supervised Fine-Tuning) backend for MoE models using AMX SIMD: Core C++ implementation: - sft_moe.hpp: Forward/backward with LoRA fused operations (~5500 lines) - moe-sft-tp.hpp: Tensor-parallel wrapper for multi-NUMA - amx/moe-sft-tp.hpp: AMX-specific TP implementation - avx_kernels.hpp: AVX512 SIMD kernels for LoRA GEMM - amx_kernels.hpp: AMX tile kernels for Panel5 rank-outer optimization - worker_pool: RDTSC profiling, Chrome trace output, SFT timer infrastructure - ext_bindings.cpp: SFT MOE pybind bindings (BF16/INT8/INT4 + SkipLoRA variants) Python sft/ submodule (kt_kernel.sft): - base.py: BaseSFTMoEWrapper with buffer management (template method pattern) - amx.py: AMXSFTMoEWrapper (weight loading, C++ task construction) - autograd.py: KTMoEFunction (torch.autograd.Function for distributed training) - layer.py: KTMoELayerWrapper (nn.Module replacing HF MoE layers) - arch.py: MOEArchConfig (Qwen3/DeepSeek/Mixtral architecture detection) - weights.py: Expert weight extraction and checkpoint loading - lora.py: PEFT LoRA adaptation (view buffers, grad buffers, save/load adapter) - wrapper.py: wrap_moe_layers_with_kt_wrapper, load_kt_model, build_kt_device_map - config.py: KTConfig dataclass (DeepSpeed-style opaque config passthrough) - dist_utils.py: Distributed gather/scatter, checkpoint-phase detection Design decisions: - Rank-0-only expert pattern: only rank 0 holds C++ wrapper and expert weights - DeepSpeed-style integration: accelerate keeps only KTransformersPlugin (framework interaction fields), all logic in kt_kernel.sft - Inference isolation: importing kt_kernel does not load sft/ submodule - Old field name compatibility: _get_kt_config() converts kt_xxx→xxx automatically Verified: Qwen3-235B-A22B 4GPU AMXBF16 training, loss converges normally.	2026-04-08 23:11:00 +08:00
mrhaoxx	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
Chen Hongtao	9e69fccb02	[feat]: add mistral moe loader compatibility (#1873) ... Co-authored-by: chenht2022 <chenht2022@users.noreply.github.com>	2026-02-28 17:50:23 +08:00
VYSE V.E.O	20262b2743	Fix Qwen3.5 FP8 load for VL detection (#1857) ... * Fix Qwen3.5 FP8 load for VL detection 1, for VL models(Qwen3.5), modify base_key: model.layers.{N} -> model.language_model.layers.{N} 2, clean DUPLICATED class BF16SafeTensorLoader(SafeTensorLoader) , only the first overrided one. * Indent type 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>	2026-02-26 15:47:22 +08:00
Jianwei Dong	16a8b98f3e	support qwen3.5 (#1846)	2026-02-16 15:48:14 +08:00
Jiaqi Liao	db82d99fa6	feat: add fallback expert prefix lookup in loader.py from kimi_k2.5 (#1822)	2026-01-30 14:09:38 +08:00
Oql	6277da4c2b	support GLM 4.7 (#1791) ... support GLM 4.7	2026-01-13 17:36:25 +08:00
Oql	5edc456749	support Native BF16 format MoE. (#1788) ... support Native BF16 format MoE	2026-01-12 14:43:28 +08:00
ErvinXie	d8046e1bb4	Kt minimax (#1742) ... [feat]: fp8 kernel and kt-cli support	2025-12-24 15:39:44 +08:00
Jiaqi Liao	fcf8882075	[Feature] Add avx-based kimi-k2 support (#1656) ... * support Kimi-K2-Thinking original weight fix amx kernel bug * update k2 avx kernel. * feat: add CPUInfer write buffer task * [feat]: add kimi k2 cpu write buffer support - Implement write_weights_to_buffer function in k2-moe.hpp for extracting GPU expert weights - Fix down (w2) weight column-wise slicing for different TP configurations - Support three TP scenarios: cpu_tp == gpu_tp, cpu_tp > gpu_tp, cpu_tp < gpu_tp - Add comprehensive test cases for weight extraction validation - Ensure compatibility with Kimi model's MoE architecture * [fix]: correct write_weight_scale_to_buffer expert offset calculation Fixed the bug in write_weight_scale_to_buffer_task where expert offsets in GPU buffers were incorrectly calculated. Changed from using per_expert_gpu sizes to using full gpu_tp sizes, ensuring correct memory layout for multi-expert scenarios. Also added benchmark scripts for k2 moe and write buffer operations, and cleaned up debug output in test files. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * [feat]: add write buffer wrapper * [fix] fix comment --------- Co-authored-by: ouqingliang <1692110604@qq.com> Co-authored-by: Claude <noreply@anthropic.com>	2025-12-02 16:01:07 +08:00
Jiaqi Liao	94c25626dc	Fix kt-kernel for new wrapper (#1588) ... * update README for kt-kernel * style: format C++ and Python code in kt-kernel - Format C++ files: task_queue, ext_bindings, and MoE operators - Format Python utility modules: amx, llamafile, and loader - Improve code readability and consistency	2025-11-10 21:47:34 +08:00
Jiaqi Liao	9bc00e587b	Refactor KTMoEWrapper backend (#1587) ... * universal backend for cpu inference * expert defer	2025-11-10 20:26:15 +08:00