Vast technology differences simultaneously
COMPUTING
-
Dell GB10s Cluster Runs Trinity-Large 398B Model 17-18 Tokens
By
–
3x Dell GB10s, 128GB unified memory each, 384GB memory for the cluster, mesh connected over 200Gbps QSFP, currently running Trinity-Large-Thinking (398B) Q4_K_M 17-18 t/s. Will review this model in time. Using as coding agent and via Hermes. pic.twitter.com/u2fKP1V0NE
— Harrison Kinsley (@Sentdex) 8 avril 20263x Dell GB10s, 128GB unified memory each, 384GB memory for the cluster, mesh connected over 200Gbps QSFP, currently running Trinity-Large-Thinking (398B) Q4_K_M 17-18 t/s. Will review this model in time. Using as coding agent and via Hermes.
-
Meta Unveils Muse Spark and Contemplating Mode
By
–
BREAKING : META ANNOUNCED MUSE SPARK, THE FIRST MSL MODEL, AND A NEW MUSE SPARK CONTEMPLATING MODE! Muse Spark Contemplating mode scored 58.4% on HLE with tools! "We’re also releasing Contemplating mode, which orchestrates multiple agents that reason in parallel. This allows
-
Larger Models in Development with Open-Source Plans
By
–
7/ this is step one. bigger models are already in development with infrastructure scaling to match. private api preview open to select partners today, with plans to open-source future versions. incredibly proud of the MSL team. excited for what’s to come!
-
Hedged Requests Reduce P99.99 DRAM Read Latency
By
–
Hedged requests (apparently inspired by the Tail at Scale paper by myself and Luiz Barroso) applied within a single machine to replicating data across DRAM channels and issuing reads to all channels, using the one that comes back first. ~5-15X reduction in p99.99 read latency.
-
GPU Prefill RDU Decode Intel Xeon Agentic AI Optimization
By
–
Inference isn’t just one thing. GPUs → prefill
RDUs → decode
Intel Xeon 6 → agentic execution With @Intel + SambaNova, every stage is optimized. Real-world AI starts here → https://
bit.ly/4mdrSiM -
Google’s TurboQuant: Have You Tried This Technology?
By
–
Interesting have you tried googles turboquant?
-
Tenstorrent Announces AI Hardware Deployment May 1st
By
–
May 1st. See it for yourself. https://
tenstorrent.com/deploy -
ACM Prize Honors Matei Zaharia for Distributed Data Systems
By
–
We're incredibly proud to congratulate our co-founder and CTO, @matei_zaharia
, on receiving the ACM Prize in Computing for his development of distributed data systems that have enabled large-scale machine learning, analytics, and AI. Matei's open-source contributions have -
Humachineology: Evolving Technohuman Competencies Framework
By
–
Humachineology and humachinekind provide a framework to study how technohuman competencies have been evolving over time.