How Taalas “prints” LLM onto a chip? (anuragk.com) | HN Screenshots

YHacker Newsscreenshots

Screenshot of anuragk.com: How Taalas “prints” LLM onto a chip?

First screen, captured 8 months ago.

Looks similar

Screenshot of verse.systems: Using LLMs to Generate Fuzzers

Using LLMs to Generate Fuzzers (verse.systems)

136 points by moyix 2 years ago | 23 comments

Screenshot of neutree.ai: Nano-vLLM: How a vLLM-style inference engine works

Nano-vLLM: How a vLLM-style inference engine works (neutree.ai)

265 points by yz-yu 8 months ago | 26 comments

Screenshot of vllm.ai: Speculative Decoding in vLLM on AMD GPUs

Speculative Decoding in vLLM on AMD GPUs (vllm.ai)

130 points by ankitg12 1 month ago | 47 comments

Screenshot of publish.obsidian.md: We fine-tuned Llama 405B on AMD GPUs

We fine-tuned Llama 405B on AMD GPUs (publish.obsidian.md)

452 points by felarof 2 years ago | 87 comments

Felafax blog post describing how they fine-tuned Llama 3.1 405B on 8 AMD MI300X GPUs using JAX, covering parameter sharding and LoRA.

llama jax amd-mi300x fine-tuning

Screenshot of lukasschwarz.de: Protocol Analysis and Libusb Linux Driver for the Uni-T UT61B Multimeter (2014)

Protocol Analysis and Libusb Linux Driver for the Uni-T UT61B Multimeter (2014)(lukasschwarz.de)

39 points by osivertsson 3 years ago | 9 comments

Screenshot of scheatkode.com: Hot-wiring the Lisp machine

Hot-wiring the Lisp machine (scheatkode.com)

28 points by spudlyo 6 months ago | 2 comments