https://pixelarity.com/parallelism
A unique, filmstrip-inspired portfolio design. Features an image gallery and a slew of settings to customize its look and feel.
parallelismpixelarity
https://engineering.fb.com/2025/10/17/ai-research/scaling-llm-inference-innovations-tensor-parallelism-context-parallelism-expert-parallelism/
Nov 13, 2025 - At Meta, we are constantly pushing the boundaries of LLM inference systems to power applications such as the Meta AI App. We’re sharing how we developed...
scalingllminferenceinnovationstensor
https://html5up.net/uploads/demos/parallelism/
parallelism
https://news.livebook.dev/speech-to-text-with-whisper-timestamping-streaming-and-parallelism-oh-my---launch-week-2---day-2-36osSY?utm_source=thinkingelixir&utm_medium=shownotes
Explore the improved Whisper integration with Livebook v0.11. Features include real-time streaming, audio timestamping, and faster processing.
speechtextwhisperstreamingparallelism
https://rocm.blogs.amd.com/software-tools-optimization/vllm-moe-guide/README.html
Learn how to combine TP, DP, PP, and EP for MoE models. Discover proven strategies to maximize performance on your vLLM deployments.
practical guidevllmmoeplaybooktp
https://html5up.net/parallelism
A unique, interactive (and fully responsive) portfolio site template. Super simple to use and loaded with plenty of customization settings. Demo images by...
parallelism
https://quantumcomputing.id/pengetahuan-dasar/apa-itu-quantum-parallelism
Pelajari bagaimana paralelisme kuantum memungkinkan komputer kuantum memproses data lebih cepat dan efisien dibandingkan komputer klasik.
apaituquantumparallelismdan
https://thenewstack.io/python-to-drop-the-global-lock-for-greater-parallelism/
Feb 13, 2025 - Big data user Meta has pledged three engineer years to creating a version of Python without global locks.
pythondropgloballockgreater
https://developer.nvidia.com/blog/scaling-large-moe-models-with-wide-expert-parallelism-on-nvl72-rack-scale-systems/
Jan 8, 2026 - Modern AI workloads have moved well beyond single-GPU inference serving. Model parallelism, which efficiently splits computation across many GPUs…
scalinglargemoemodelswide
https://www.graphcore.ai/posts/exploiting-tile-level-parallelism-on-graphcore-ipus
An IPU consists of many cores called tiles: its 1472 tiles can run completely independent programs. Here, we explain how to optimise a simple Poplar codelet to...
exploitingtilelevelparallelismgraphcore