From 4909db7bb9112217fe2e86d0fa1ac5c97bf9523c Mon Sep 17 00:00:00 2001 From: Nate W Date: Thu, 7 May 2026 18:06:19 -0700 Subject: [PATCH] LFX 2026 Term 2 projects posted to LFX - batch 4 Moves three Volcano projects (AgentCube multi-agent, Kthena third-party model APIs, Kthena Router benchmark) from project_ideas.md into the accepted projects list in README.md. Assisted-by: Copilot <223556219+Copilot@users.noreply.github.com> Signed-off-by: Nate W --- .../lfx-mentorship/2026/02-Jun-Aug/README.md | 58 +++++++++++++++++++ .../2026/02-Jun-Aug/project_ideas.md | 45 -------------- 2 files changed, 58 insertions(+), 45 deletions(-) diff --git a/programs/lfx-mentorship/2026/02-Jun-Aug/README.md b/programs/lfx-mentorship/2026/02-Jun-Aug/README.md index 640114a2d..3e6156b67 100644 --- a/programs/lfx-mentorship/2026/02-Jun-Aug/README.md +++ b/programs/lfx-mentorship/2026/02-Jun-Aug/README.md @@ -118,6 +118,11 @@ Mentee application instructions can be found on the [Program Guidelines](https:/ - [Improving DNS and localhost based networking compatibility for urunc across CNIs](#improving-dns-and-localhost-based-networking-compatibility-for-urunc-across-cnis) - [Integration of urunc's sandbox execution with Argo](#integration-of-uruncs-sandbox-execution-with-argo) - [Volcano](#volcano) + - [AgentCube](#agentcube) + - [Support multi-AgentCube Capability](#support-multi-agentcube-capability) + - [kthena](#kthena) + - [Kthena Router Benchmark](#kthena-router-benchmark) + - [Kthena Router supports APIs for third-party models](#kthena-router-supports-apis-for-third-party-models) - [Scheduler Management, Observability & Log Explorer UI](#scheduler-management-observability-log-explorer-ui) - [Support Namespace-scoped Queue in Volcano](#support-namespace-scoped-queue-in-volcano) - [WasmEdge](#wasmedge) @@ -1676,6 +1681,59 @@ CNCF - Volcano: Support Namespace-scoped Queue in Volcano (2026 Term 2) - Upstream Issue: https://github.com/volcano-sh/volcano/issues/5251 - LFX URL: https://mentorship.lfx.linuxfoundation.org/project/9e582ac4-4e12-4fcc-a1cd-27855d79730a +#### AgentCube + +##### Support multi-AgentCube Capability + +CNCF - Volcano: AgentCube - Support multi-AgentCube Capability (2026 Term 2) + +- Description: At present, AgentCube launches a single agent for both Code Interpretation and agent runtime. However, we have now entered the era of multi-agent collaboration. Consequently, AgentCube aims to support multi-AgentCube orchestration, enabling multiple agents to collaborate on a single task, with AgentCube providing unified management of the lifecycle of these agents. +- Expected Outcome: + 1. Proposal + 2. Code(Including Unit test and E2E test) + 3. User guide and another related docs. +- Recommended Skills: + - Go, Kubernetes, agent +- Mentor(s): + - Zhonghu xu(@hzxuzhonghu, zhhxu2011@gmail.com), + - ZhenCheng Li(@LiZhenCheng9527, lizhencheng6@huawei.com), +- Upstream Issue: https://github.com/volcano-sh/agentcube/issues/301 +- LFX URL: https://mentorship.lfx.linuxfoundation.org/project/9e7dd1c1-5d14-4c5e-af43-83454099e490 + +#### kthena + +##### Kthena Router supports APIs for third-party models + +CNCF - Volcano: Kthena Router supports APIs for third-party models (2026 Term 2) + +- Description: At present, the Kthena router provides robust support for routing within the cluster. However, during discussions with customers, some users have expressed a need for the ability to integrate with external large language model APIs. Consequently, the Kthena community plans to use this LFX to enable the router to access third-party LLM APIs. +- Expected OUtcome: + 1. Proposal + 2. Code(Include unit test. It would be even better if end-to-end testing were included. However, external LLM APIs are unlikely to offer stable, long-term free access, so end-to-end testing is not a prerequisite.) + 3. User Guide and related documents. +- Recommended: Go, Kubernetes, Network, LLM. +- Mentor(s): Zengzeng Yao(@yaozengzeng, yaozengzeng@huawei.com) +- Upstream Issue: https://github.com/volcano-sh/kthena/issues/939 +- LFX URL: https://mentorship.lfx.linuxfoundation.org/project/baa6fb1f-58c9-4255-849c-21aca35ce5e1 + +##### Kthena Router Benchmark + +CNCF - Volcano: Kthena Router Benchmark (2026 Term 2) + +- Description: Kthena Router is the LLM routing component in the Volcano/Kthena project, responsible for forwarding inference requests to in-cluster and (soon) third-party model backends. As Kthena gradually matures, the community needs a reproducible benchmark to understand the router's performance characteristics (throughput, latency, tail latency, resource usage) under realistic LLM traffic patterns, and to detect regressions across releases. This project asks the mentee to design and implement a benchmark framework for Kthena Router, produce a complete report. Where the benchmark surfaces clear bottlenecks or inefficiencies, the mentee will also work with maintainers to land code-level optimizations upstream. +- Expected Outcome: + - A reusable benchmark framework for Kthena Router (load generator, scenario configs, metrics collection, result aggregation), runnable locally and in CI. + - A defined set of test scenarios covering typical LLM routing patterns (varying QPS, prompt/response sizes, concurrency, number of backends, routing strategies). + - End-to-end test procedure documented as a runbook (cluster setup, mock/real backends, how to run, how to interpret results). + - A benchmark report with metrics (throughput, TPOT, TTFT, GPU/CPU/memory) and analysis of bottlenecks. + - Upstream PR(s) implementing optimizations for any clear hotspots identified, with before/after numbers. +- Recommended Skills: Go, Kubernetes, performance benchmarking and profiling (pprof), basic familiarity with LLM inference and HTTP/gRPC routing. +- Mentor(s): + - Zengzeng Yao (@yaozengzeng, yaozengzeng@huawei.com), + - Zhonghu Xu (@hzxuzhonghu, zhhxu2011@gmail.com), +- Upstream Issue: https://github.com/volcano-sh/kthena/issues/942 +- LFX URL: https://mentorship.lfx.linuxfoundation.org/project/1cf34cb5-3520-4f15-81c8-4258cb9abcb9 + ### WasmEdge #### Memory alignment in WASM instructions diff --git a/programs/lfx-mentorship/2026/02-Jun-Aug/project_ideas.md b/programs/lfx-mentorship/2026/02-Jun-Aug/project_ideas.md index b4bdcd1ff..49c2748ce 100644 --- a/programs/lfx-mentorship/2026/02-Jun-Aug/project_ideas.md +++ b/programs/lfx-mentorship/2026/02-Jun-Aug/project_ideas.md @@ -18,48 +18,3 @@ ## Proposed Project ideas -### Volcano - -#### AgentCube - -##### Support multi-AgentCube Capability - -- Description: At present, AgentCube launches a single agent for both Code Interpretation and agent runtime. However, we have now entered the era of multi-agent collaboration. Consequently, AgentCube aims to support multi-AgentCube orchestration, enabling multiple agents to collaborate on a single task, with AgentCube providing unified management of the lifecycle of these agents. -- Expected Outcome: - 1. Proposal - 2. Code(Including Unit test and E2E test) - 3. User guide and another related docs. -- Recommended Skills: - - Go, Kubernetes, agent -- Mentor(s): - - Zhonghu xu(@hzxuzhonghu, zhhxu2011@gmail.com), - - ZhenCheng Li(@LiZhenCheng9527, lizhencheng6@huawei.com), -- Upstream Issue: https://github.com/volcano-sh/agentcube/issues/301 - -#### kthena - -##### Kthena Router supports APIs for third-party models - -- Description: At present, the Kthena router provides robust support for routing within the cluster. However, during discussions with customers, some users have expressed a need for the ability to integrate with external large language model APIs. Consequently, the Kthena community plans to use this LFX to enable the router to access third-party LLM APIs. -- Expected OUtcome: - 1. Proposal - 2. Code(Include unit test. It would be even better if end-to-end testing were included. However, external LLM APIs are unlikely to offer stable, long-term free access, so end-to-end testing is not a prerequisite.) - 3. User Guide and related documents. -- Recommended: Go, Kubernetes, Network, LLM. -- Mentor(s): Zengzeng Yao(@yaozengzeng, yaozengzeng@huawei.com) -- Upstream Issue: https://github.com/volcano-sh/kthena/issues/939 - -##### Kthena Router Benchmark - -- Description: Kthena Router is the LLM routing component in the Volcano/Kthena project, responsible for forwarding inference requests to in-cluster and (soon) third-party model backends. As Kthena gradually matures, the community needs a reproducible benchmark to understand the router's performance characteristics (throughput, latency, tail latency, resource usage) under realistic LLM traffic patterns, and to detect regressions across releases. This project asks the mentee to design and implement a benchmark framework for Kthena Router, produce a complete report. Where the benchmark surfaces clear bottlenecks or inefficiencies, the mentee will also work with maintainers to land code-level optimizations upstream. -- Expected Outcome: - - A reusable benchmark framework for Kthena Router (load generator, scenario configs, metrics collection, result aggregation), runnable locally and in CI. - - A defined set of test scenarios covering typical LLM routing patterns (varying QPS, prompt/response sizes, concurrency, number of backends, routing strategies). - - End-to-end test procedure documented as a runbook (cluster setup, mock/real backends, how to run, how to interpret results). - - A benchmark report with metrics (throughput, TPOT, TTFT, GPU/CPU/memory) and analysis of bottlenecks. - - Upstream PR(s) implementing optimizations for any clear hotspots identified, with before/after numbers. -- Recommended Skills: Go, Kubernetes, performance benchmarking and profiling (pprof), basic familiarity with LLM inference and HTTP/gRPC routing. -- Mentor(s): - - Zengzeng Yao (@yaozengzeng, yaozengzeng@huawei.com), - - Zhonghu Xu (@hzxuzhonghu, zhhxu2011@gmail.com), -- Upstream Issue: https://github.com/volcano-sh/kthena/issues/942