Tessera
Folgen

AIME

@aime-hq.bsky.social

AIME provides GPU cloud compute and develops AI-machines for deep learning and model inference (Multi-GPU workstations & HPC servers). We are in Berlin, Germany.

248 Posts442 Follower1544 Folgt
AIME@aime-hq.bsky.social · 3mo ago

TurboQuant compresses LLM KV-caches via 3-bit key & 2/4-bit value quantization, cutting memory use by up to 4.4×. Enables longer contexts & higher throughput under GPU constraints. Open-source (GPL-3.0). github.com/0xSero/turboquant #LLM #Inference #Quantization #vLLM #OpenSource

GitHub - 0xSero/turboquant: TurboQuant: Near-optimal KV cache quantization for LLM inference (3-bit keys, 2-bit values) with Triton kernels + vLLM integration

TurboQuant: Near-optimal KV cache quantization for LLM inference (3-bit keys, 2-bit values) with Triton kernels + vLLM integration - 0xSero/turboquant

github.com

AIME@aime-hq.bsky.social · 4mo ago

Robbyant released LingBot-Map A new feed-forward 3D foundation model for streaming-based reconstruction – now open source. ✨ Geometric Context Transformer ⚡ ~20 FPS streaming inference 🏆 SOTA results on multiple benchmarks 💻 github.com/Robbyant/lin...

GitHub - Robbyant/lingbot-map: A feed-forward 3D foundation model for reconstructing scenes from streaming data

A feed-forward 3D foundation model for reconstructing scenes from streaming data - Robbyant/lingbot-map

github.com

AIME@aime-hq.bsky.social · 5mo ago

SakanaAI's new Text-to-LoRA (T2L) uses a hypernetwork to generate task-specific LoRAs from simple text descriptions—no expensive fine-tuning required. ✅ Compresses 100s of adapters ✅ Generalizes to unseen tasks ✅ ICML 2025 Paper & Code: github.com/SakanaAI/tex...

GitHub - SakanaAI/text-to-lora: Hypernetworks that adapt LLMs for specific benchmark tasks using only textual task description as the input

Hypernetworks that adapt LLMs for specific benchmark tasks using only textual task description as the input - SakanaAI/text-to-lora

github.com

AKI.IO@aki-io.bsky.social · 6mo ago

AKI.IO is now live: Curated open-source and open-weight models such as #MiniMax M2.5, #Apertus 70B, #Qwen Image Edit and many more as an API – hosted entirely in European data centers w/o hyperscalers. Happy to get your feedback! The playground is open, API key via free registration at aki.io

Home - AKI.IO

Token-based access to leading open-source AI models on EU infrastructure. Evaluate, build and scale your AI product without self-hosting or vendor lock-in.

aki.io

AIME@aime-hq.bsky.social · 6mo ago

Qwen3.5 is out: Alibaba's open-weight series built for agentic AI with native multimodality. ✅ Flagship: 397B total / 17B active params (MoE) ✅ 1M-token context → 2h audio/video in one pass ✅ 60% cheaper, 8× more efficient than predecessor ✅ MIT license, full open weights github.com/QwenLM/Qwen3.5

GitHub - QwenLM/Qwen3.5: Qwen3.5 is the large language model series developed by Qwen team, Alibaba Cloud.

Qwen3.5 is the large language model series developed by Qwen team, Alibaba Cloud. - QwenLM/Qwen3.5

github.com

AIME@aime-hq.bsky.social · 6mo ago

GLM-5 is Z.ai's new MoE flagship (744B total/40B active) built for agentic engineering. ✅ #1 open-source on Vending Bench 2 ✅ Closes gap with Claude Opus on CC-Bench-V2 ✅ DeepSeek Sparse Attention for efficient 200K context ✅ Apache 2.0 license, commercial use allowed github.com/zai-org/GLM-5

GitHub - zai-org/GLM-5: GLM-5: From Vibe Coding to Agentic Engineering

GLM-5: From Vibe Coding to Agentic Engineering. Contribute to zai-org/GLM-5 development by creating an account on GitHub.

github.com

AIME@aime-hq.bsky.social · 6mo ago

ACE-Step v1.5 is out: an open-source music generation model that runs locally with <4 GB VRAM. 8 diffusion steps → full songs in ~2s (A100) 4-min tracks with lyrics, 50+ languages MIT license, full training code included A leap for accessible, commercial-grade audio AI 👇 github.com/ace-step/ACE...

GitHub - ace-step/ACE-Step-1.5: The most powerful local music generation model that outperforms most commercial alternatives, supporting Mac, AMD, Intel, and CUDA devices.

The most powerful local music generation model that outperforms most commercial alternatives, supporting Mac, AMD, Intel, and CUDA devices. - ace-step/ACE-Step-1.5

github.com

AIME@aime-hq.bsky.social · 6mo ago

Qwen3-ASR drops: open-source speech recognition that transcribes speech, music, and singing across 52 languages — with accuracy rivaling GPT-4o and Gemini. 1.7B & 0.6B variants. Unified streaming/offline inference. Apache 2.0. github.com/QwenLM/Qwen3...

GitHub - QwenLM/Qwen3-ASR: Qwen3-ASR is an open-source series of ASR models developed by the Qwen team at Alibaba Cloud, supporting stable multilingual speech/music/song recognition, language detectio...

Qwen3-ASR is an open-source series of ASR models developed by the Qwen team at Alibaba Cloud, supporting stable multilingual speech/music/song recognition, language detection and timestamp predicti...

github.com

AIME@aime-hq.bsky.social · 7mo ago

Kimi released K2.5 — a native multimodal model trained on 15T visual-text tokens that generates full interactive UIs from prompts and orchestrates 100-agent swarms for complex tasks. 4.5× faster execution, 59% productivity boost. Open weights available now. www.kimi.com/blog/kimi-k2...

Kimi K2.5: Visual Agentic Intelligence | Technical Report

Kimi K2.5 defines Visual Agentic Intelligence. Trained on 15T tokens, it introduces SOTA visual coding and autonomous agent swarm. Read the full tech report.

kimi.com

AIME@aime-hq.bsky.social · 7mo ago

Alibaba released Qwen3-TTS, a new text-to-speech model with discrete multi-codebook LM architecture under Apache license. Features 97ms synthesis latency, 3-second voice cloning, and 10-language support including German. Available on Hugging Face and ModelScope. github.com/QwenLM/Qwen3...

GitHub - QwenLM/Qwen3-TTS: Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice...

Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice...

github.com