Models & Labs
Ex-OpenAI researcher launches Jev System 1 model
Fireshipmedium confidence
Why it matters
- →Removes text generation overhead to drastically reduce inference costs and latency.
- →Challenges the industry standard that all capable AI must possess language capabilities.
- →Offers a potential new architecture for specialized, high-speed reasoning tasks.
Former OpenAI researcher Diogo Almeida has launched Jev, an AI model designed without text generation capabilities. The system focuses exclusively on 'System 1' fast thinking, claiming to be 200 times faster and 400 times cheaper than conventional large language models while remaining hallucination-free. By removing the ability to write code or speak, the model targets high-throughput, low-latency applications where natural language output is not required.
Read originalMore in Models & Labs
Models & Labsmodels
vLLM v0.30.0: DeepSeek V4.1 and Fast Start
This release is a massive infrastructure overhaul for serving the latest reasoning models. The headline feature is native support for DeepSeek-V4.1-Flash, storing its entire KV cache in MXFP8 on SM100 hardware to drastically reduce memory overhead. For operators tired of slow cold starts, the new Fast Start daemon caches post-quantized weights in GPU memory, allowing engines to map over CUDA IPC instead of reloading from disk. It also brings HiSparse, a host-resident tier that spills KV pages to pinned host memory under pressure, effectively expanding usable context windows without buying more GPUs.
vLLM Releases
Models & Labsother
llama.cpp b11080 release with ROCm 10 and CUDA 13
This update quietly extends llama.cpp’s hardware support to ROCm 10.0 and CUDA 13.4 across Linux and Windows, keeping the library competitive as NVIDIA pushes newer driver stacks. The test suite also gains regex filtering for backend operations, a practical improvement for developers debugging specific inference paths. While no new model architectures are introduced, this release ensures compatibility with the latest GPU ecosystems without forcing users to wait for major version bumps.