antirez
@antirez
Reproducible bugs are candies.
I like programming too much for not liking automatic programming.
801 Following 81.4K Followers
At this point DwarfStar contains many fast fused kernels for important model families: feel free to steal everything you want from there according to the MIT license, in order to improve your own implementation.
Show more
Witch hunting level: some guy uses AI to reverse engineer an M4 GPU driver for Linux and part of the community that should be for the open source, for the hacking, for the liberation and freedom is against him.
Show more
The irreconcilable misunderstanding about AI is that for some of us is the way to remove suffering, inequality, limits from the human race. For others, a tool: and, right now, the capabilities are at tool level, giving the illusion that the tool is the point.
Show more
Please when listening to people that have the absolute truth at disposal, make sure to check the track record in the latest few years.
@PessimistsArc Right. Dario was already claiming that GPT2 was too dangerous to open source back in 2019.
I made fun of them then.
Everyone should make fun of them now.
It drive me nuts that now people use AI to write tweets. If you think that this way you will get more popular and so forth, think twice. Write something authentic. AI is great but it is easy to misuse. Your tweets must be your more cared thoughts.
Show more
Conspiracy theories are, very often, illogical. If AI companies were worried by open weight models (they probably are btw) the logical response would be to *not* slow down the development of frontier AI, to try locking the advantage. Stop with nonsense.
Show more
Thanks @antirez for the recent ds4 updates and YouTube video. Phenomenal work! I retrofitted experimental DeepSeek V4.1 steering to the CLI/server and published three adapters with provenance. Behavioral validation still pending.
Show more
Btw somebody should report numbers of DwarfStar running DS4.1 Flash on a 256GB M5 Ultra, so see what the speed difference is. Agreed on thermals btw, even if there are ways to avoid most problems actually... But instead of talking about them I'll simply implement them :D
Show more
If you think at it, there are very little reasons to spend the same money for a Mac Studio M5 Ultra with 256GB of RAM if you can get, for the same price, 2x Macbook Pro with 128GB RAM and an RDMA cable. It is just a matter of developing good inference software. Do you agree?
Show more
If you think at it, there are very little reasons to spend the same money for a Mac Studio M5 Ultra with 256GB of RAM if you can get, for the same price, 2x Macbook Pro with 128GB RAM and an RDMA cable. It is just a matter of developing good inference software. Do you agree?
Show more
It works well (as expected) on the M3 Ultra with 256GB of RAM. I did my full residency tests on the 512GB version provided via SSH by friends.
It drives me *nuts* that YouTube auto dubbing works great on the videos I record in English, if you select the Italian audio track, but not the fucking reverse. Since my Italian is much better than my English, imagine how broken it must be the IT->EN dubbing.
Show more
DeepSeek v4.1 Flash support is now pushed on DwarfStar "main" branch on GitHub, and this is a YouTube video (in English language) where I test both the SSD streamed and the dual MacBook m5 max 128GB setup during a coding session:
Show more
🚨 MiniMax H3 is RIGHT HERE in Draw Things！Go try it NOW！
🔄 Draw Things v26.0910.1 was released in the iOS / macOS AppStore 2 hours ago. This version brings:
🔹 Support MiniMax H3 series models, including LoRAs and TeaCache;
🔹 Support importing Krea 2 series models.
🔹 Fix some performance issues on M4 Apple Neural Engine.
gRPServerCLI and draw-things-cli both are updated to 26.0910.1 with above related updates.
Show more
About Anthropic banning minors from using Claude.
DwarfStar running DeepSeek v4.1 Flash on a 128GB M5 Max. I didn't expect with SSD streaming it could be so fast. Recent SSD streaming changes to retain the right experts surely helped, but also maybe DS4.1 uses the same experts more. Will push online when ready QA > ASAP.
Show more
Can’t make this up…the MacBook is using its webcam to look at its screen in a mirror to improve AMD Radeon chip support in Omarchy.
P.S. I believe the credits should go exclusively to Córdoba–Martínez-Zoroa and AI.
Enjoy the DwarfStar glm-5.3-flash branch with GLM 5.3 Flash Q2 and Q4 support: single MacBook 128GB or DGX Spark inference, two MacBook RDMA 128GB each Q4 inference in tensor parallel fashion at 37 t/s single generation. ~500 t/s prefill for now, can be higher. ROCm soon.
Show more
Exactly. One of the many hard to understand limits of a very closed ecosystem.
I really hope @Apple will allow a way to manually set CPU/GPU frequency in their Apple Silicon chips.
High Power is too much, Low Power is too little.
We'd like to be able to adjust this based on our needs.
Show more
THE ANNOUNCEMENT: We’re going to make the prophecy of The Year of Linux on the Desktop come true. All the pieces are now in place. Time to go all in!
