mirror of
https://github.com/kvcache-ai/ktransformers.git
synced 2025-09-08 05:29:29 +00:00
ef89b1520b
* Consolidate the installation section, as it's currently too cluttered
* Move the Multi-GPU section to the top-level structure
* Add a **detailed** tutorial on registering extra GPU memory with Marlin
|
||
|---|---|---|
| .. | ||
| BigCodeBench.png | ||
| cpuinfer.png | ||
| DeepSeek-on-KTransformers.png | ||
| deepseekv2_structure.png | ||
| Framework_effect.png | ||
| InfLLM_equation.jpg | ||
| InfLLM_framework.png | ||
| InjectStruction.png | ||
| internlm_memory.png | ||
| KTransformers.png | ||
| KTransformers_long_context_v1.png | ||
| KTransformers_long_context_v2.png | ||
| long_context_generate.png | ||
| long_context_prefill.png | ||
| model_structure_guild.png | ||
| multi_gpu.png | ||
| needle_1M.png | ||
| needle_128K.png | ||
| Quest_framework.png | ||
| SnapKV_framework.png | ||
| SparQ_attention.png | ||
| website.png | ||
