@yar_vol@FireworksAI_HQ Yes, it’s deployed on fireworks.ai , but public endpoints have a more throughput-optimized setup. There is no ‘one size fits all’ when it comes to performance. To get the cutting edge latencies described in the post you would need a private endpoint setup.
21 Followers 125 FollowingSpecialist data consultancy with 50+ engineers delivering data strategy, migration & managed services across modern cloud platforms.
115 Followers 2K FollowingDirector Success Architect at https://t.co/uPcdJ7TsLI, Salesforce CTA, Passionate about Technology and Engineering. All opinions are my personal opinions.
699 Followers 3K FollowingMission: Neural networks everywhere
Manager of Agentic Staff. GPUs @Meta. Opinions stated here are my own, not those of my current employer.
3K Followers 402 FollowingI’m a software engineer building high-performance kernels and compilers at Anthropic! Previously at Facebook/Meta (PyTorch, HHVM, ReDex)
11K Followers 531 FollowingAuthor of PyTorch, Research Scientist at Google DeepMind. Currently working on Pallas, Mosaic and dex-lang. MIMUW CS & Math graduate. [email protected]
56K Followers 1K FollowingCofounded & running @ml_collective. Weekly talks at Deep Learning Classics & Trends (DLCT). Research at Google DeepMind. DEI/DIA Chair of ICLR & NeurIPS.
597K Followers 3K FollowingNVIDIA Director of Robotics & Distinguished Scientist. Co-Lead of GEAR lab. Solving Physical AGI, one motor at a time. Stanford Ph.D. OpenAI's 1st intern.
49K Followers 918 FollowingCreator of bitsandbytes. Professor @CarnegieMellon and Research Scientist @allen_ai . I blog about deep learning and PhD life at https://t.co/Y78KDJJFE7.
22K Followers 1K FollowingAssocProf @CarnegieMellon. Distinguished Eng @NVIDIA. Creator of @XGBoostProject, @ApacheTVM. Member https://t.co/QYyfjQNp4p, @TheASF. Views are on my own
3K Followers 402 FollowingI’m a software engineer building high-performance kernels and compilers at Anthropic! Previously at Facebook/Meta (PyTorch, HHVM, ReDex)
863K Followers 367 FollowingTogether with the AI community, we are pushing the boundaries of what’s possible through open science to create a more connected world.