Submissions from modal.com

		Three types of LLM workloads and how to serve them (modal.com)
		74 points by charles_irl 1 day ago \| past \| 5 comments
		LLM architecture has evolved from GPT-2 to GPT-OSS (2025) (modal.com)
		2 points by jxmorris12 2 days ago \| past \| discuss
		Keeping 20k GPUs Healthy (modal.com)
		3 points by aburan28 3 days ago \| past \| discuss
		Keeping 20k GPUs healthy (modal.com)
		115 points by jxmorris12 4 days ago \| past \| 57 comments
		High-Performance LLM Inference (modal.com)
		1 point by birdculture 8 days ago \| past \| discuss
		Keeping 20k GPUs Healthy (modal.com)
		2 points by MasterScrat 10 days ago \| past \| discuss
		Keeping 20k GPUs Healthy (modal.com)
		3 points by birdculture 10 days ago \| past \| discuss
		Keeping 20,000 GPUs Healthy (modal.com)
		1 point by susam 11 days ago \| past \| discuss
		Keeping 20k GPUs Healthy (modal.com)
		3 points by birdculture 12 days ago \| past \| discuss
		Keeping 20k GPUs Healthy (modal.com)
		3 points by birdculture 13 days ago \| past \| 1 comment
		What Is Arithmetic Bandwidth? (modal.com)
		2 points by jxmorris12 14 days ago \| past
		Keeping 10k GPUs Healthy (modal.com)
		2 points by birdculture 14 days ago \| past \| 1 comment
		GPU memory snapshots: sub-second startup (2025) (modal.com)
		27 points by jxmorris12 14 days ago \| past \| 13 comments
		Sandboxed Claude Code GIF Creator (modal.com)
		1 point by birdculture 17 days ago \| past
		Agents need good developer experience too (modal.com)
		1 point by birdculture 19 days ago \| past
		Host overhead is killing your inference efficiency (modal.com)
		3 points by birdculture 33 days ago \| past
		Agents need good developer experience too (modal.com)
		2 points by birdculture 36 days ago \| past
		Agents need good developer experience too (modal.com)
		2 points by birdculture 47 days ago \| past
		Agents need good developer experience too (modal.com)
		1 point by birdculture 51 days ago \| past
		Agents need good developer experience too (modal.com)
		1 point by birdculture 54 days ago \| past
		Agents need good developer experience too (modal.com)
		3 points by birdculture 56 days ago \| past \| 1 comment
		Agents need good developer experience too (modal.com)
		1 point by birdculture 61 days ago \| past
		Agents need good developer experience too (modal.com)
		3 points by birdculture 63 days ago \| past
		Host overhead is killing your inference efficiency (modal.com)
		3 points by birdculture 64 days ago \| past
		Host overhead is killing your inference efficiency (modal.com)
		3 points by charles_irl 65 days ago \| past
		One-Second Voice-to-Voice Latency with Modal, Pipecat, and Open Models (modal.com)
		1 point by birdculture 68 days ago \| past
		One second voice-to-voice latency with just open models (modal.com)
		3 points by birdculture 74 days ago \| past
		1 second voice-to-voice latency with all open models (modal.com)
		3 points by birdculture 77 days ago \| past
		We built a cloud GPU notebook that boots in seconds (modal.com)
		91 points by birdculture 81 days ago \| past \| 34 comments
		CUDA Docs for Humans (modal.com)
		2 points by helloplanets 3 months ago \| past
		More