41554 blogs · 4,417,066 posts Claim your blog

Record · corpus.blog/posts/01a07d5d-88d1-7203-af2c-4b784fd47cd6

Modular: MAX GPU: State of the Art Throughput on a New GenAI platform

Modular · published 17 December 2024

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at modular.com Wayback capture

0blogs citing

First cited: —
Most recent: —
Rank this month: not ranked
Links from this post: 10
Words captured: 2,841

Cited by

No blog we hold has cited this post yet.

Links from this post

Link

Host

https://www.modular.com/blog/how-to-be-confident-in-your-performance-benchmarking

modular.com

https://docs.modular.com/max/tutorials/benchmark-max-serve/

docs.modular.com

https://hao-ai-lab.github.io/blogs/distserve/

hao-ai-lab.github.io

https://en.wikipedia.org/wiki/Goodput

en.wikipedia.org

https://blog.vllm.ai/2024/09/05/perf-update.html

blog.vllm.ai

https://forum.modular.com/

forum.modular.com

https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered

huggingface.co

https://github.com/vllm-project/vllm/blob/main/benchmarks/benchmark_serving.py

github.com

https://github.com/modularml/max/blob/nightly/pipelines/benchmarking/benchmark_serving.py

github.com

https://github.com/vllm-project/vllm/blob/main/.buildkite/nightly-benchmarks/tests/nightly-tests.json

github.com