Recent Blog Posts
-
Google Puts TPUv7 Through an Outside Agentic Benchmark
by Chris DePuy, 650 Group / October 25, 2026 Google’s first TPUv7 submission to an outside agentic-inference benchmark landed this week. The operator’s October 14, 2026 announcement reports FP8 results served through vLLM at 1.67x better performance per dollar than NVIDIA’s GB300 NVL72 at FP4 the operator’s announcement thread. The submission is the first submitted…
-
DeepSeek Open-Sources DeepInfer, NVIDIA Answers Quietly With Flare
by Chris DePuy, 650 Group / October 22, 2026 In the early hours of October 20, Pacific time, DeepSeek announced DeepInfer, its in-house inference framework, as fully open source under the Apache 2.0 license. DeepInfer is the stack that powers DeepSeek-V4.1-Flash at scale in the company’s own production services. The four-post thread laid out the…
-
The Spark Fleet Learns to Run Itself
by Chris DePuy, 650 Group / October 21, 2026 The last month of desk-side serving stories were about engines. Athena put two frontier models on one 128 GB box at 262K context with a 141,519-token conversation restored from disk in 2.1 seconds; Imprint turned that same restore trick into a standalone context-cache service with a…
-
Five Spark Clusters, Two Kinds of Proof: TP5 GLM-5.3 Runs as Beam Sets the Efficiency Bar
by Chris DePuy, 650 Group / October 6, 2026 Five DGX Sparks now carry the full 753-billion-parameter GLM-5.3: an operator reported the first working five-board tensor-parallel build on Monday, with 1.5 million tokens of KV cache, prefill above 2,000 tokens per second, and 76 tokens per second single-stream — rising to 98–113 tokens per second…
-
Cloudflare’s Sharp Course Correction to AI
by Chris DePuy, 650 Group / October 5, 2026 Cloudflare closed its 16th Birthday Week on October 5 with 46 announcements across open source, post-quantum security, AI agents, and developer platform upgrades, and the occasion invites a wider read than one launch week. We scanned every post the company published on blog.cloudflare.com over the last…
-
Three Jev Alternates Landed in a Week: Cloudflare Clef, JEV-27B-VL, and the Open Decision-Model Family
by Chris DePuy, 650 Group / October 2, 2026 Three developments inside a week have moved decision models — the System One models that return typed, calibrated probabilities instead of generated prose — from a single hosted API into a crowded open-weights field. Cloudflare shipped two Apache-2.0 decision models, Clef and Clef-flash, post-trained from frozen…
-
System One Comes to the Agent Stack: Jev, Its Uses, and Its Open-Weight Alternatives
TypeSafe AI’s launch of Jev has spawned dozens of open reproductions in a week — and forced a clearer question than the benchmark race: which decisions in an agent loop ever needed a language model? by Chris DePuy, 650 Group / September 28, 2026 On September 14, 2026, TypeSafe AI released Jev, the first public…
-
New TensorFold LLM Model Serving Software Dramatically Improves Decode Speed on Macs and Sparks
by Chris DePuy, 650 Group / September 27, 2026 Two repositories shipped from one maintainer this week and made the same promise in two different places. On September 25 and 26, a developer publishing under the name Ash Hart released TensorFold, a local inference engine for Apple Silicon and NVIDIA GPUs, and Imprint, a tool…
-
NVIDIA’s Official NVFP4 Checkpoints for DeepSeek-V4.1-Flash and GLM-5.3-Flash: Four DGX Sparks Read the Receipts
by Chris DePuy / September 22, 2026 NVIDIA: what the conversion actually changes The DeepSeek checkpoint converts only the ordinary routed experts — projections w1, w2 and w3 across 384 experts in 40 layers — from the source MXFP4 format to NVFP4 weights and activations at group size 16, per the model card; attention, shared…
Top 10 Companies
Agentic AI AI Agents AI Infrastructure ConnectX-7 DeepSeek DeepSeek V4.1-Flash Deskside AI DFlash DGX Spark DSpark FP8 GB10 GLM-5.3-Flash Kimi K3 KV Cache Local-Inference long context MoE MXFP4 NVFP4 NVIDIA Open Weights Quantization Qwen RoCE SGLang Speculative Decoding TensorFold Tensor Parallelism vLLM