#llm
0:38
Sensitive content
This media may contain sensitive content.
0:38
Sensitive content
This media may contain sensitive content.
"We've developed what we believe is a sufficient, joint weapon target pairing Large Language Model (LLM) that will run inside the kill chain. We started out developing this in an #INDOPACOM exercise..we are now moving to evolve that from a simple #LLM to an actually fully devolved reasoning model that we are modeling after the Field Artillery Warrant Officer" ~ Col. Jonathan Harvey (📹US Army)
AirPower 2.0 (MIL_STD)69,169 次观看 • 7 个月前
Check out mistral.rs, our #Rust-based open source inference engine allowing for fast #LLM serving for a variety of architectures including X-LoRA mixture-of-expert (MoE) models, Llama-3, Mistral/Mixtral, Gemma & many others. Built on the Hugging Face #Candle framework for #Rust w/ custom CUDA kernels in the backend (as well as support for Metal, Apple Accelerate, and Intel MKL for CPU use), you can easily create a REST API OpenAI compatible server or run via Python bindings. Key features include: ✅Prefix caching, continuous batching ✅Flash Attention V2 ✅Device offloading ✅GGUF or Hugging Face models ✅2, 3, 4, 5, 6 and 8 bit quantization ✅X-LoRA MoE non-granular scalings for fast inference ✅Grammar support ✅Continuous batching ✅LoRA support with weight merging ✅LlamaIndex 🦙 integration ...and much more. Incorporation into our GraphReasoning multi-agent modeling framework & LlamaIndex 🦙 allows you to combine in-context learning with adversarial agentic strategies, to dive deep into complex scientific analyses, such as to predict material behaviors, generate hypotheses, analyze papers and data, develop new research concepts, and much more. Check out mistral.rs: Join our Discord here: Rust Trending Rust Language
Markus J. Buehler73,575 次观看 • 2 年前