GitLab

Merge branch 'fix_precision_MLA' of https://github.com/kvcache-ai/ktransformers into server-prefix-cache

Update install.md

Update SUMMARY.md

[fix] Mock triton mla due to precision issue

toy support for experts on GPU, no CUDA Graph

thanks..., I was about to submit and found that you had already modified it. Thank you for your contribution

ensure that gguf_path argument is a directory.

Update DeepseekR1_V3_tutorial.md

📝 fix typo

[feature] update  docker image and entrypoint

📝 update V0.2.1 Doc

Atream add adapted

[update]  Reorganize documentation/README

    * 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

Revert "[update] Reorganize documentation/README"

[update] Reorganize documentation/README

warm_up before capture