Open Issues Need Help
View All on GitHub Nightly load test of router overhead 16 days ago
help wanted good first issue testing roadmap
mishraprafful/multihull mishraprafful/multihull Deploy always-warm GPU inference containers to many providers from one spec. One URL, automatic per-request failover. Built for reliability over cost.
Open project →
0
Deploy always-warm GPU inference containers to many providers from one spec. One URL, automatic per-request failover. Built for reliability over cost.
Python
#failover#gpu#high-availability#inference#kubernetes#llm-serving#load-balancer#mlops#modal#model-serving#python#rust
Harness: flapping provider scenario 16 days ago
help wanted good first issue testing roadmap
mishraprafful/multihull mishraprafful/multihull Deploy always-warm GPU inference containers to many providers from one spec. One URL, automatic per-request failover. Built for reliability over cost.
Open project →
0
Deploy always-warm GPU inference containers to many providers from one spec. One URL, automatic per-request failover. Built for reliability over cost.
Python
#failover#gpu#high-availability#inference#kubernetes#llm-serving#load-balancer#mlops#modal#model-serving#python#rust
help wanted good first issue router roadmap
mishraprafful/multihull mishraprafful/multihull Deploy always-warm GPU inference containers to many providers from one spec. One URL, automatic per-request failover. Built for reliability over cost.
Open project →
0
Deploy always-warm GPU inference containers to many providers from one spec. One URL, automatic per-request failover. Built for reliability over cost.
Python
#failover#gpu#high-availability#inference#kubernetes#llm-serving#load-balancer#mlops#modal#model-serving#python#rust
Translator conformance suite 16 days ago
help wanted good first issue provider testing
mishraprafful/multihull mishraprafful/multihull Deploy always-warm GPU inference containers to many providers from one spec. One URL, automatic per-request failover. Built for reliability over cost.
Open project →
0
Deploy always-warm GPU inference containers to many providers from one spec. One URL, automatic per-request failover. Built for reliability over cost.
Python
#failover#gpu#high-availability#inference#kubernetes#llm-serving#load-balancer#mlops#modal#model-serving#python#rust