kvcache-ai/Mooncake

[TE] Refactor: unify libfabric-based transports (EFA / CXI) shared infrastructure

Aperta

#2657 aperta il 29 giu 2026

 (3 commenti) (0 reazioni) (0 assegnatari)C++ (803 fork)auto 404
good first issue

Metriche repository

Star
 (5470 stelle)
Metriche merge PR
 (Merge medio 4g 6h) (224 PR mergiate in 30 g)

Descrizione

Background

With #2535 (CXI backend) merged, we now have two transports built on libfabric that share significant structural overlap but are implemented as independent forks. This was the pragmatic choice for initial integration (see discussion in #2535), but leaves maintenance debt.

Scope

  1. Topology — CXI currently reuses InfiniBand device discovery paths in topology.cpp. CXI is not IB; it should have its own topology functions or a shared libfabric_topology abstraction (ref: @alogfans' comment).

  2. Shared base class or utilities — Extract common libfabric patterns (endpoint management, CQ polling, MR registration, error handling) into a shared layer that both EFA and CXI can consume, reducing duplicated code.

  3. mr_key_t consolidation — The current #if defined(USE_EFA) || defined(USE_CXI) guards work but will grow unwieldy if more libfabric providers are added. Consider a compile-time or runtime abstraction.

Non-goals

  • Changing the public API or metadata wire format
  • Merging EFA and CXI into a single transport (they have meaningful behavioral differences in MR handling and transfer semantics)

References

  • #2535 — CXI backend PR
  • #2564 — 64-bit MR key fix

Guida contributor