vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2026-04-28 03:39:48 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4
kvcache-ai-ktransformers/doc/assets
History
Jiaqi Liao 57d14d22bc
Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 
* refactor: move legacy code to archive/ directory

  - Moved ktransformers, csrc, third_party, merge_tensors to archive/
  - Moved build scripts and configurations to archive/
  - Kept kt-kernel, KT-SFT, doc, and README files in root
  - Preserved complete git history for all moved files

* refactor: restructure repository to focus on kt-kernel and KT-SFT modules

* fix README

* fix README

* fix README

* fix README

* docs: add performance benchmarks to kt-kernel section

Add comprehensive performance data for kt-kernel to match KT-SFT's presentation:
- AMX kernel optimization: 21.3 TFLOPS (3.9× faster than PyTorch)
- Prefill phase: up to 20× speedup vs baseline
- Decode phase: up to 4× speedup
- NUMA optimization: up to 63% throughput improvement
- Multi-GPU (8×L20): 227.85 tokens/s total throughput with DeepSeek-R1 FP8

Source: https://lmsys.org/blog/2025-10-22-KTransformers/

This provides users with concrete performance metrics for both core modules,
making it easier to understand the capabilities of each component.

* refactor: improve kt-kernel performance data with specific hardware and models

Replace generic performance descriptions with concrete benchmarks:
- Specify exact hardware: 8×L20 GPU + Xeon Gold 6454S, Single/Dual-socket Xeon + AMX
- Include specific models: DeepSeek-R1-0528 (FP8), DeepSeek-V3 (671B)
- Show detailed metrics: total throughput, output throughput, concurrency details
- Match KT-SFT presentation style for consistency

This provides users with actionable performance data they can use to evaluate
hardware requirements and expected performance for their use cases.

* fix README

* docs: clean up performance table and improve formatting

* add pic for README

* refactor: simplify .gitmodules and backup legacy submodules

- Remove 7 legacy submodules from root .gitmodules (archive/third_party/*)
- Keep only 2 active submodules for kt-kernel (llama.cpp, pybind11)
- Backup complete .gitmodules to archive/.gitmodules
- Add documentation in archive/README.md for researchers who need legacy submodules

This reduces initial clone size by ~500MB and avoids downloading unused dependencies.

* refactor: move doc/ back to root directory

Keep documentation in root for easier access and maintenance.

* refactor: consolidate all images to doc/assets/

- Move kt-kernel/assets/heterogeneous_computing.png to doc/assets/
- Remove KT-SFT/assets/ (images already in doc/assets/)
- Update KT-SFT/README.md image references to ../doc/assets/
- Eliminates ~7.9MB image duplication
- Centralizes all documentation assets in one location

* fix pic path for README
2025-11-10 17:42:26 +08:00
..
amx.png update doc 2025-04-28 18:24:15 +00:00
amx_avx.png update doc 2025-04-28 18:24:15 +00:00
amx_intro.png update doc 2025-04-28 18:24:15 +00:00
BigCodeBench.png Initial commit 2024-07-27 16:06:58 +08:00
cpuinfer.png Initial commit 2024-07-27 16:06:58 +08:00
DeepSeek-on-KTransformers.png Fix incorrect image content in the document 2025-02-14 09:04:22 +00:00
deepseekv2_structure.png Update readme; add pipeline tutorial; add detailed inject tutorial 2024-08-15 20:42:54 +08:00
Framework_effect.png [feature] release 0.1.3 2024-08-28 16:11:43 +00:00
heterogeneous_computing.png Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 2025-11-10 17:42:26 +08:00
image-20250801165752484.png add the docs and update README for KSFT 2025-11-04 05:51:48 +00:00
image-20250801174517784.png add the docs and update README for KSFT 2025-11-04 05:51:48 +00:00
image-20250801174623919.png add the docs and update README for KSFT 2025-11-04 05:51:48 +00:00
image-20250911184023795.png add the docs and update README for KSFT 2025-11-04 05:51:48 +00:00
image-20250911184455749.png add the docs and update README for KSFT 2025-11-04 05:51:48 +00:00
image-20251011010558909.png add the docs and update README for KSFT 2025-11-04 05:51:48 +00:00
image-20251016171526210.png add the docs and update README for KSFT 2025-11-04 05:51:48 +00:00
image-20251016171537997.png add the docs and update README for KSFT 2025-11-04 05:51:48 +00:00
image-20251016175046882.png add the docs and update README for KSFT 2025-11-04 05:51:48 +00:00
image-20251016175848143.png add the docs and update README for KSFT 2025-11-04 05:51:48 +00:00
image-20251016182810716.png add the docs and update README for KSFT 2025-11-04 05:51:48 +00:00
image-20251016182920722.png add the docs and update README for KSFT 2025-11-04 05:51:48 +00:00
image-20251016182942726.png add the docs and update README for KSFT 2025-11-04 05:51:48 +00:00
image-compare_model.png add the docs and update README for KSFT 2025-11-04 05:51:48 +00:00
InfLLM_equation.jpg [feature] release 0.1.3 2024-08-28 16:11:43 +00:00
InfLLM_framework.png [feature] release 0.1.3 2024-08-28 16:11:43 +00:00
InjectStruction.png Initial commit 2024-07-27 16:06:58 +08:00
internlm_memory.png [feature] release 0.1.3 2024-08-28 16:11:43 +00:00
KTransformers.png Initial commit 2024-07-27 16:06:58 +08:00
KTransformers_long_context_v1.png [feature] release 0.1.3 2024-08-28 16:11:43 +00:00
KTransformers_long_context_v2.png [feature] release 0.1.3 2024-08-28 16:11:43 +00:00
long_context_generate.png [feature] release 0.1.3 2024-08-28 16:11:43 +00:00
long_context_prefill.png [feature] release 0.1.3 2024-08-28 16:11:43 +00:00
model_structure_guild.png Update readme; add pipeline tutorial; add detailed inject tutorial 2024-08-15 20:42:54 +08:00
multi_gpu.png Update readme; add pipeline tutorial; add detailed inject tutorial 2024-08-15 20:42:54 +08:00
needle_1M.png [feature] release 0.1.3 2024-08-28 16:11:43 +00:00
needle_128K.png [feature] release 0.1.3 2024-08-28 16:11:43 +00:00
onednn_1.png update doc 2025-04-28 18:24:15 +00:00
Quest_framework.png [feature] release 0.1.3 2024-08-28 16:11:43 +00:00
SnapKV_framework.png [feature] release 0.1.3 2024-08-28 16:11:43 +00:00
SparQ_attention.png [feature] release 0.1.3 2024-08-28 16:11:43 +00:00
website.png Initial commit 2024-07-27 16:06:58 +08:00
演示文稿1_01.png add the docs and update README for KSFT 2025-11-04 05:51:48 +00:00
风格化数据集模型输出对比_01.png add the docs and update README for KSFT 2025-11-04 05:51:48 +00:00