B200s
PulseAugur coverage of B200s — every cluster mentioning B200s across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
Ripple-65B LLM requires custom builds for local execution
The Ripple-65B large language model is now available for local execution, though it requires specific configurations and patched software. Standard tools like Ollama and the default llama.cpp build cannot load the model…
-
Disaggregated Serving on B200s: Performance and Cost Analysis
This article discusses the performance and cost implications of disaggregated serving on B200 hardware. The author admits that previous measurements were conducted on hardware that was not fully capable of the task. The…
-
Thinking Machines launches Inkling multimodal AI model on Modal
Thinking Machines has launched Inkling, a new multimodal AI model capable of processing text, images, and audio to generate text outputs. This model, featuring a mixture-of-experts architecture with 975 billion total pa…
-
New speculative decoding methods boost LLM inference speed and safety
Researchers are developing advanced speculative decoding techniques to accelerate large language model inference. HyperDFlash optimizes decoding for DeepSeek-V4's multi-hyper-connection architecture, improving draft acc…
-
AI GPU shortage questioned amid findings of significant underutilization
A recent analysis of GPU utilization in AI workloads suggests that the perceived shortage of high-end GPUs like NVIDIA's H100s and Blackwell B200s may be exacerbated by underutilization. The GPU in question spent a sign…
-
Together Compute Expands GPU Offerings with H100, H200, and B200
Together, an inference and open-source AI company, has significantly expanded its on-demand compute platform. The company announced the addition of a substantial number of high-end GPUs, including H100s, H200s, and the …