LoreonLabsPlatform

Overview

Intelligence

Markets
Builders
Research
Narratives
Ecosystems
Launchpads

Discover

Search
Sources

Other

llm-d-kv-cache

Distributed KV cache scheduling & offloading libraries

OtherEmerging

Stars

—

Forks

—

Contributors

8

Last push

3d ago

Recent commits

Latest commits.

feat: batch KV block copies via cudaMemcpyBatchAsync in fs connector (#607)
59aa98fKfir Toledo15d ago
fs_backend: migrate kv_offload API to vllm 0.22.0 (#628)
7fa4f3dKfir Toledo15d ago
style(fs-backend): collapse double blank line in thread_pool.cpp (#634)
777e78cKfir Toledo16d ago
fix: remove MIN_STAGING_BUFFER_SIZE that inflates KV cache on disk (#589)
0bdacb2Jonathan Wrede16d ago
deps(go): bump the go-dependencies group across 1 directory with 16 updates (#630)
886e931dependabot[bot]

16d ago

ci: Wire fs_backend Python tests into CI (#578)

6e5f7daalberto17d ago

feat: Add PVC evictor BlockRemoved events (#605)

545a46ealberto18d ago

fix Dockerfile.dev breakage (#620)

c8fff80Saikat Roychowdhury18d ago

Top contributors

Builders behind this project.