corpus.blog
56,966 blogs · 4,417,066 posts Claim your blog
Record · corpus.blog/posts/01a0879a-41af-73b5-b047-e92fd1fd6bc1

It's not the compute, it's the memory bandwidth

levischuck.com · published undated

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 levischuck.com Wayback capture
0blogs citing
First cited
—
Most recent
—
Rank this month
not ranked
Links from this post
41
Words captured
1,356

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
https://en.wikipedia.org/wiki/Pipeline_stall
en.wikipedia.org
https://en.wikipedia.org/wiki/Cache_performance_measurement_and_metric
en.wikipedia.org
https://en.wikipedia.org/wiki/Locality_of_reference
en.wikipedia.org
https://en.wikipedia.org/wiki/Just-in-time_compilation
en.wikipedia.org
https://store.steampowered.com/app/1091500/Cyberpunk_2077/
store.steampowered.com
https://ollama.com/
ollama.com
https://en.wikipedia.org/wiki/Dynamic_random-access_memory
en.wikipedia.org
https://en.wikipedia.org/wiki/Static_random-access_memory
en.wikipedia.org
https://en.wikipedia.org/wiki/I/O_bound
en.wikipedia.org
https://en.wikipedia.org/wiki/CPU-bound
en.wikipedia.org
https://www.apple.com/newsroom/2026/03/apple-introduces-macbook-pro-with-all-new-m5-pro-and-m5-max/
apple.com
https://www.nvidia.com/en-us/geforce/graphics-cards/50-series/rtx-5090/
nvidia.com
https://www.nvidia.com/en-us/data-center/h100/
nvidia.com
https://unsloth.ai/docs/models/tutorials/glm-4.7
unsloth.ai
https://en.wikipedia.org/wiki/Remote_direct_memory_access
en.wikipedia.org
https://huggingface.co/docs/accelerate/en/usage_guides/distributed_inference
huggingface.co
https://siliconmatter.substack.com/p/the-memory-wall-and-its-implications
siliconmatter.substack.com
https://en.wikipedia.org/wiki/Neural_processing_unit
en.wikipedia.org
https://www.macrumors.com/2026/03/05/mac-studio-no-512gb-ram-upgrade/
macrumors.com
https://docs.cloud.google.com/tpu/docs/system-architecture-tpu-vm
docs.cloud.google.com
https://docs.cloud.google.com/tpu/docs/tpu7x
docs.cloud.google.com
https://groq.com/newsroom/groq-and-nvidia-enter-non-exclusive-inference-technology-licensing-agreement-to-accelerate-ai-inference-at-global-scale
groq.com
https://groq.com/blog/the-groq-lpu-explained
groq.com
https://en.wikipedia.org/wiki/High_Bandwidth_Memory
en.wikipedia.org
https://www.tomshardware.com/pc-components/ram/memory-prices-now-shifting-hourly-as-smaller-firms-fight-over-scraps
tomshardware.com
https://rcrtech.com/semiconductor-news/memory-wall-why-hbm-importance/
rcrtech.com
https://qwen.ai/research
qwen.ai
https://techcrunch.com/2026/03/03/alibabas-qwen-tech-lead-steps-down-after-major-ai-push/
techcrunch.com
https://taalas.com/the-path-to-ubiquitous-ai/
taalas.com
https://pr.tsmc.com/english/news/1989
pr.tsmc.com
https://www.eetimes.com/taalas-specializes-to-extremes-for-extraordinary-token-speed/
eetimes.com
https://bizety.com/2025/12/28/the-dirty-dram-deal-how-openai-just-locked-up-40-of-global-ram/
bizety.com
https://en.wikipedia.org/wiki/Thunderbolt_(interface
en.wikipedia.org
https://en.wikipedia.org/wiki/PCI_Express
en.wikipedia.org
https://en.wikipedia.org/wiki/Differential_signalling
en.wikipedia.org
https://www.i-pex.com/library/article/what-is-pam
i-pex.com
https://www.imdb.com/title/tt0081633/
imdb.com
https://twitter.com/_Freakyclown_
twitter.com
https://www.luckfox.com/
luckfox.com
https://www.espressif.com/
espressif.com
https://onnx.ai/
onnx.ai