Here is DeepSeek 4.1 Flash running on @Qualcomm Cloud AI 100 Ultra (4x4 SoCs) with @zml_ai. This is a world first afaik.
1
2
1,362
Corendos retweeted
Announcing ZML/LLMD 20260929.0, with DeepSeek 4.1 Flash support zml.ai/posts/llmd-20260929.0…
5
27
4,660
Damn That shit so easy lol
We got access to @Qualcomm's AI100 on sunday. How fast can we make @zml_ai (and zml/llmd) run on them? The answer is less than 24 hours. Bringing the number of architectures that run ZML to 12: - CPU - NVIDIA - AMD - Intel - Apple Metal - Vulkan - Google TPUs - Tenstorrent - AWS Trainium - Moore Threads - Furiosa NPU - Qualcomm NPU And still zero Python.
3
628
Cette cascade a été réalisée sans trucage. Deepseek V4.1 Flash in LLMD: ✅
3 hours later: DeepSeek 4.1 Flash Day 0 in ZML/LLMD
1
324
Corendos retweeted
In close collaboration with @poolsideai, we’re happy to announce the support of Laguna S 2.1, their new open-weight model for agentic coding and long-horizon work. It’s available today in ZML/LLMD with DFlash support. Most importantly (and as always with us), it’s available on all the supported platforms: NVIDIA, AMD, Intel, Google TPU and Apple Metal. It's a good model, sir. zml.ai/posts/laguna-s-2-1/
Today we're releasing Laguna S 2.1, our most capable model to date. It's a 118B total parameter Mixture-of-Experts model with 8B activated per token, a context window of up to 1M tokens, and thinking and no-thinking modes. Capable enough to hold its own against models many times its size. Small enough to run on a single @NVIDIAAI DGX Spark. Laguna S 2.1 is fully open under OpenMDW-1.1, with weights available today on @huggingface poolside.ai/blog/introducing…
1
6
49
7,161
Zero-day support of Gemma 4 in llmd
Gemma 4 31B-it BF16 rough draft on @zml_ai, zero performance work yet
230
Corendos retweeted
Introducing zml-smi, a universal diagnostic and monitoring tool for GPUs, TPUs and NPUs. Real-time insights into the performance and health of your hardware. Read & Download: zml.ai/posts/zml-smi/
3
26
139
19,265
Corendos retweeted
ZML/v2 is live !
Introducing ZML/v2 ZML/v2 is a complete rewrite of the framework with a focus on developer experience, performance and most importantly composability. Link in next tweet.
2
8
49
3,640
We completely reworked the way ZML is designed from the ground up. Nobody will be able to catch up. Go check it out.
Introducing ZML/v2 ZML/v2 is a complete rewrite of the framework with a focus on developer experience, performance and most importantly composability. Link in next tweet.
4
112
Corendos retweeted
zml-smi running on TPU, Inferentia, NVIDIA and AMD same binary, because of course.
2
5
68
4,889
Americans saw that and went for highways and billboards instead
1
119
Ça regarde son pays se faire baiser par les autres sans rien faire et c'est moi le cuck mdr + Web3 dans la bio -> opinion discarded
1
351
For the love of god @EmbarkStudios please make a way to select PvE only lobbies in Arc Raiders, I don't want to spend more time with those fucking sub-humans that are forcing PvP
1
1
743
>be Sarah Knafo >want to make Paris great again >be me >ask if it's an ideological or pragmatic plan >"It's a good plan sir" >look inside >it's 100% ideological
1
558
Trésor national, je veux rien savoir
Breaking: Statue of Liberty reportedly spotted swimming back across the Atlantic. Said she “preferred the original terms and conditions.” 🇫🇷
551
Found the midwit ↓
elon is the man of the millennium and most people still don't understand why it's not the money. bezos has money. it's not the companies. plenty of founders have companies. it's that he's the only one treating civilizational survival as an engineering problem instead of a talking point
296
Corendos retweeted
Gradium is out of stealth to solve voice. We raised $70M and after only 3 months we’re releasing our transcription and synthesis products to power the next generation of voice AI.
80
155
1,144
490,465