Infera Development Roadmap (2026 Q3)
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 21
- Forks
- 4
- Avg merge
- 2d 7h
- Merged PRs (30d)
- 28
Description
Infera Development Roadmap (2026 Q3)
Planned work by category — current state and the target.
| Category | Item | Today | Goal |
|---|---|---|---|
| Model support | Multimodal (image / audio / video) | Routed on load only (no cache locality) | MM-aware routing; encode/prefill/decode (EPD) separation |
| Hardware support | MI325 / MI300 | Validated on MI355X only | Validate + CI on MI325 / MI300 |
| PD / networking / comms | Transports | RDMA (Mooncake / MoRI / NIXL); xGMI diagnostics only | Evaluate xGMI / remote-copy for intra-node KV |
| Parallelism | Wide expert parallelism (EP) | Not supported | 32+ GPU instances spanning nodes |
| KV-cache management | Offload engine coverage | vLLM only (incl. AIC GPU-Direct) | SGLang (incl. GPU-Direct), then ATOM |
| KV-cache management | Cluster-wide KV pool | L3 or L4 (either/or) | Composed L3 + L4; multi-model namespacing |
| KV-cache management | Distributed prefill cache | Per worker | Shared across prefill workers and with decoders |
| Operator optimization | Op injection | HyperLoom Optimized OP Injection | Cross-engine op/kernel injection using HyperLoom optimized by new model and user workload |
| Framework | Dynamic scaling (Kubernetes) [DONE] | Dynamic Scaling, by api, ratio and replica | Load-driven autoscaling; runtime role switching |
| Framework | SLA-aware scheduling | Relative cost heuristic; throughput only | Settable SLO targets and goodput reporting |
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
This issue is a broad 2026 Q3 roadmap covering multimodal routing, hardware validation, transports, parallelism, KV-cache management, operator injection, Kubernetes scaling, and SLA scheduling. No files, tests, entry points, or bounded acceptance criteria are named. Start by selecting one roadmap item and locating its implementation area; the work is done only when that item has a specific scope and verifiable target.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- kubernetes, python
- Domain
- backend, cloud, distributed-systems, infrastructure
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100