Siemens Digital Industries Software launched a fork of llama.cpp that tests expert expansion on MoE models with Apple Metal
Public source
Publisher name
Public post
llama.cpp fork tests expert expansion on MoE models with Apple Metal
Company
Siemens Digital Industries Software
- Industry
- Software Development
- Location
- Plano, US
- Company size
- 10,001+ employees
About Siemens Digital Industries Software
We help organizations of all sizes digitally transform using software, hardware and services from the Siemens Xcelerator business platform. Our software and the comprehensive digital twin enable companies to optimize their design, engineering and manufacturing processes to turn today's ideas into the sustainable products of the future. From chips to entire systems, from product to process, across all industries. We help transform the everyday as part of @Siemens, To learn more, visit http://sw.siemens.com.
See moreLatest activity
Latest activity from Siemens Digital Industries Software
106 signals
Products & Services
Siemens Digital Industries Software implemented Opcenter Advanced Planning and Scheduling software across two production facilities for Peccin S.A.
People
Siemens Digital Industries Software is hiring an Applications Engineer for FPGA Prototyping and chip verification in San Diego, CA.
People
Siemens Digital Industries Software is hiring a Senior Applications Engineer for Emulation and Verification roles in San Diego, Costa Mesa, Austin, or Wilsonville.
Discover more
Similar signals
Similar public activity from other companies.
Research & Knowledge
Databricks
Databricks found that Llama 3.1 8B Instruct was the fastest model in the synthetic workload, but only 34 out of 100 passed.
Research & Knowledge
Runway
Runway published new research on Solaris, our first Interface World Model, which finds that Solaris outperforms frontier LLMs when generating new interfaces across structural similarity and information retention.
Research & Knowledge
Google launched Gemini 3.8 Flash, which tops the DeepSWE v1.1 benchmark.
Research & Knowledge
Together AI
Together AI published research on QLoRA to compress the base model to 4 bits and reduce memory usage to 1/4, allowing the base model plus 16-bit adapters to fit on a smaller GPU.
Products & Services
Hugging Face