[PR #511] [CLOSED] [Store] Python store API supports batch operation #1617

New issue

Closed

opened 2026-10-29 21:28:56 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-29 21:28:56 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/kvcache-ai/Mooncake/pull/511
Author: @xinranwang17
Created: 6/17/2025
Status: ❌ Closed

Base: main ← Head: python-batch-api

📝 Commits (2)

4286794 Python store API supports batch operation
2a4e266 Update store_py.cpp

📊 Changes

11 files changed (+377 additions, -24 deletions)

View changed files

📝 mooncake-integration/store/store_py.cpp (+225 -23)
📝 mooncake-integration/store/store_py.h (+26 -0)
📝 mooncake-store/include/client.h (+8 -0)
📝 mooncake-store/include/master_client.h (+8 -0)
📝 mooncake-store/include/master_service.h (+7 -0)
📝 mooncake-store/include/rpc_service.h (+22 -1)
📝 mooncake-store/proto/master.proto (+19 -0)
📝 mooncake-store/src/client.cpp (+8 -0)
📝 mooncake-store/src/master_client.cpp (+25 -0)
📝 mooncake-store/src/master_service.cpp (+9 -0)
📝 mooncake-store/tests/client_integration_test.cpp (+20 -0)

📄 Description

This PR introduces batch APIs (put_batch, get_batch, is_batch_exist) in the Python module to accelerate data transfer. These APIs are concurrently utilized in the Mooncake store implementation as the L3 cache in SGLang.
Related PR in sglang

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/kvcache-ai/Mooncake/pull/511 **Author:** [@xinranwang17](https://github.com/xinranwang17) **Created:** 6/17/2025 **Status:** ❌ Closed **Base:** `main` ← **Head:** `python-batch-api` --- ### 📝 Commits (2) - [`4286794`](https://github.com/kvcache-ai/Mooncake/commit/4286794f557c65b8ad5462929b9428a499eced56) Python store API supports batch operation - [`2a4e266`](https://github.com/kvcache-ai/Mooncake/commit/2a4e2663e2bd7e0c598674d6bdc09cfa124f02c3) Update store_py.cpp ### 📊 Changes **11 files changed** (+377 additions, -24 deletions) <details> <summary>View changed files</summary> 📝 `mooncake-integration/store/store_py.cpp` (+225 -23) 📝 `mooncake-integration/store/store_py.h` (+26 -0) 📝 `mooncake-store/include/client.h` (+8 -0) 📝 `mooncake-store/include/master_client.h` (+8 -0) 📝 `mooncake-store/include/master_service.h` (+7 -0) 📝 `mooncake-store/include/rpc_service.h` (+22 -1) 📝 `mooncake-store/proto/master.proto` (+19 -0) 📝 `mooncake-store/src/client.cpp` (+8 -0) 📝 `mooncake-store/src/master_client.cpp` (+25 -0) 📝 `mooncake-store/src/master_service.cpp` (+9 -0) 📝 `mooncake-store/tests/client_integration_test.cpp` (+20 -0) </details> ### 📄 Description This PR introduces batch APIs (put_batch, get_batch, is_batch_exist) in the Python module to accelerate data transfer. These APIs are concurrently utilized in the Mooncake store implementation as the L3 cache in SGLang. Related [PR](https://github.com/sgl-project/sglang/pull/7211) in sglang --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi

2026-10-29 21:28:56 +00:00