Conversation
- Introduce flexkv/gpu_backend/ Python abstraction layer with GpuBackend ABC
(15 abstract methods covering memory, stream, IPC, and storage operations)
- Add NvidiaBackend (production-ready), GenericBackend (CPU fallback),
and MusaBackend (experimental) implementations
- Auto-detect backend at import time via flexkv/gpu_backend/__init__.py
- Unify C extension entry point to single flexkv.c_ext for all backends:
* csrc/gpu_backend/nvidia/gpu_transfer_bindings.h (CUDA-specific bindings)
* csrc/gpu_backend/musa/gpu_transfer_bindings.h (MUSA-specific bindings)
* csrc/bindings.cpp selects backend via #if FLEXKV_BACKEND_MUSA at compile time,
injected by MUSABuilder; ext_name is always flexkv.c_ext (no c_ext_musa branch)
- Add build_backends/ package (CUDABuilder, MUSABuilder, GenericBuilder)
with per-vendor compile flags and source lists; all comments in English
- Add docs/gpu_backends/README_zh.md and README_en.md integration guides
covering 5 design principles, step-by-step onboarding, GDS/IPC fallback;
NvidiaBackend code example updated to match actual implementation
feiqiangs
requested review from
YconquestY,
axxx03,
linhu-nv,
peaceforeverCN and
zhuofan1123
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
injected by MUSABuilder; ext_name is always flexkv.c_ext (no c_ext_musa branch)
with per-vendor compile flags and source lists; all comments in English
covering 5 design principles, step-by-step onboarding, GDS/IPC fallback;
NvidiaBackend code example updated to match actual implementation