HackerTrans
TopNewTrendsCommentsPastAskShowJobs

antinucleon

118 karmajoined 12 lat temu

Submissions

The Great Wave Has Arrived (Memo from GLM CEO Jie Tang)

twitter.com
2 points·by antinucleon·4 dni temu·0 comments

What Muse Spark 1.1 Taught Us About Enterprise Agent Architecture

int21.ai
2 points·by antinucleon·5 dni temu·0 comments

Stop Waiting for a Bigger Context Window

int21.ai
3 points·by antinucleon·8 dni temu·1 comments

Show HN: INT21 – Self-Improving PTX Kernel Factory

int21.ai
3 points·by antinucleon·29 dni temu·0 comments

7 days of autonomous agent search outperformed FlashAttention-4 and CUDNN

twitter.com
3 points·by antinucleon·4 miesiące temu·0 comments

From Node.js/Python to PTX: The first AI framework generated by AI agents

github.com
3 points·by antinucleon·6 miesięcy temu·0 comments

PetaFLOPS Inference Era: 1 Pflops Attention, and Preliminary End-to-End Results

blog.hippoml.com
2 points·by antinucleon·2 lata temu·0 comments

Unified DataCenter and Local Foundation Model Serving: Beyond Docker Way

blog.hippoml.com
4 points·by antinucleon·3 lata temu·0 comments

Super AI Creativity App Run with Local GPU on Windows/Linux/MacOS

blog.hippoml.com
19 points·by antinucleon·3 lata temu·8 comments

comments

antinucleon
·3 lata temu·discuss
Yes
antinucleon
·3 lata temu·discuss
Mojo is trying to create a new language to solve the problem, and specialized for CPU. We are using a more pragmatic way to solve GPU AI computation problem.
antinucleon
·3 lata temu·discuss
We haven't compared yet.
antinucleon
·3 lata temu·discuss
We developed AITemplate majorly for Meta's focus at that time, eg Ads/Ranking need. For HippoML is startup we are building for Generative AI. HippoML is not using AITemplate.
antinucleon
·3 lata temu·discuss
It is actually non-trivial to get GPU run fast, especially on SoC with strong CPU like M2.
antinucleon
·3 lata temu·discuss
Hippo is faster than AITemplate, and supports more generative models. We haven't compared vs TVM, but for absolute token/s on M2 Max, Hippo is able to run decoding on LLAMA with datacenter level GPUs performance (with other SW).
antinucleon
·3 lata temu·discuss
We will disclose more details very soon.
antinucleon
·3 lata temu·discuss
Yes. We support >= 1bit <= 16bit models out of box for various of models.
antinucleon
·3 lata temu·discuss
AITemplate's original designer is here. We quit Meta in January and start HippoML (https://hippoml.com/). We just disclosed our new engine's performance on LLM: https://blog.hippoml.com/large-language-model-inference-from... On Apple M2 Max our new engine encode/decode is 13.8X/2.4X faster than llama.cpp