TechiSeek

AddAdd your Listings

Blogs

Cache-aware prefill–decode disaggregation (CPD) for up to 40% faster long-context LLM serving

Together

Serving long prompts doesn’t have to mean slow responses. At Together AI, we built cache-aware prefill–decode disaggregation (CPD), a serving architecture that purposely separates cold and warm workloads by cache hit rate, resulting in fast context reuse.

Visit Site

Long context retrieval models with Monarch MixerTogether Long Context Fine-Tuning: A Technical Deep DiveTogether Preparing for the era of 32K context: Early learnings and explorationsTogether Hyena Hierarchy: Towards larger convolutional language modelsTogether Kimi K3: the complete developer guideTogether How to choose the right open model for productionTogether Grafana Is Not Worried About AWS CommercializationThenewstack When CI Meets CD: Deliver With ConfidenceThenewstack Announcing the New Pulumi Partner ProgramPulumi How We Eliminated Long-Lived CI Secrets Across 70+ ReposPulumi Supporting Kubernetes with Faster, Easier Test EnvironmentsPulumi Go Concurrency Patterns: Context - The Go Programming LanguageGo How to serve trillions of tokens for trillion-parameter coding agentsModal PostgreSQL and Ducks: The Perfect Analytical PairingMotherduck SQL is Dead, Long Live SQL: Engineering a Reliable Analytics Agent from ScratchMotherduck The rise of slow personal assistantsCerebras Simulating Human Behavior with Cerebras - CerebrasCerebras 100x Defect Tolerance: How Cerebras Solved the Yield Problem - CerebrasCerebras Cerebras Announces Six New AI Datacenters Across North America and Europe to Deliver Industry’sCerebras AMD and Cerebras Announce Disaggregated AI InferenceCerebras