yyj 41613064c7 feat(GLM): add native GLM-5.3-flash support (#2173) ...

* feat: support SwiGLU limit for block FP8 experts

* perf(fp8): add native layerwise batch transport

* feat(fp8): support layerwise transport for TP1/2/4/8

* release: prepare GLM-5.3-flash support

* docs(glm): refine GLM-5.3-flash documentation

* docs(glm): simplify release announcement

2026-08-26 22:45:12 +08:00

..

api/server

Initial commit

2024-07-27 16:06:58 +08:00

【云端低价训推】 KTransformers+AutoDL+LlamaFactory：随用随租的低成本超大模型「微调+推理」一体化流程.pdf

Add AutoDL Tutorial (#1801)

2026-01-22 14:52:47 +08:00

AVX2-Tutorial_zh.md

[feat](kt-kernel): add AVX2/AVX-VNNI RAWINT4 MoE backend (#1942)

2026-04-30 17:16:49 +08:00

clawdbot_integration_guide.md

[docs]: add clawd bot docs

2026-01-30 15:51:30 +08:00

DeepseekR1_V3_tutorial_zh_for_Ascend_NPU.md

Npu revise benchmark results and prerequisites (#1716)

2025-12-16 14:26:44 +08:00

DeepseekR1_V3_tutorial_zh.md

add flashinfer to cuda device

2025-05-15 07:03:45 +00:00

GLM-5.3-Flash-Tutorial_zh.md

feat(GLM): add native GLM-5.3-flash support (#2173)

2026-08-26 22:45:12 +08:00

KT-SFT-Checkpoint-Cache-Underflow-RCA_zh.md

[feat](kt-kernel): end-to-end full-parameter and LoRA SFT(#2094)

2026-07-23 21:23:34 +08:00

KTransformers-Fine-Tuning_Cookbook_zh.md

[docs]: add easy-to-use fine-tuning cookbook (#2169)

2026-08-25 01:13:41 +08:00

KTransformers-Fine-Tuning_Developer-Technical-Notes_zh.md

[feat](cmake & doc): fix bug with cmake arch detect & update doc for sft

2025-11-04 08:46:26 +00:00

KTransformers-Fine-Tuning_User-Guide_zh.md

fix: remove py310 as guide

2025-11-08 08:54:32 +00:00

Low-cost_Cloud_Training_and_Inference_KTransformers+AutoDL+LlamaFactory_An_On-demand_Cost-efficient_Integrated_Pipeline_for_Ultra-large_Model_Fine-tuning_and_Inference.pdf

Add files via upload (#1814)

2026-01-27 17:44:50 +08:00

Qwen3-MoE_tutorial_zh_for_Ascend_NPU.md

fix: qwen3-npu bugs; update: add readme-for-qwen3-npu (#1717)

2025-12-16 14:27:04 +08:00

Qwen3.5-SGLang-LoRA-Serving_zh.md

[docs]: clean up Qwen3.5 KT LoRA serving guide (#2057)

2026-06-23 20:52:23 +08:00

SYCL-GPTQ-INT4-Tutorial_zh.md

[feat] Add SYCL backend for intel iGPU (#2089)

2026-07-17 16:24:04 +08:00