Friday's big release was Qwen 3. 8 27B , an Apache 2 licensed 27B parameter vision-capable LLM from Alibaba's Qwen research lab.
Qwen3.8-Flash-Next is an open‑weights multimodal Mixture‑of‑Experts (MoE) model previewing the architecture of Qwen4. It contains 125 B tokens with only 6 B active, giving a performance boost. The author has tested it on a DGX Spark with Unsloth quantized models, exploring variants like UD‑IQ1_S and UD‑Q2_K_XL, and highlighted a high‑reasoning‑effort example from UD‑Q2_K_XL.
arXiv:2606. 11257v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) pipelines are compute-intensive, combining embedding, retrieval, reranking, and large language model (LLM) generation.
arXiv:2606. 09682v1 Announce Type: new Abstract: AutoMegaKernel (AMK) compiles a HuggingFace Llama-family model into a single persistent cooperative CUDA kernel that runs the whole forward pass in one launch, with no per-model hand-written CUDA.
DeepSeek V4 Pro 0813 (on OpenRouter) The latest DeepSeek Pro model is now available, via API only. I had to link to OpenRouter because DeepSeek don't have any obvious announcement page for their new model.
arXiv:2607. 23159v1 Announce Type: new Abstract: Test-time search lets small video diffusion models rival larger ones, but costs 2-10x more.
The paper presents a Pareto atlas of LLM inference optimizations, mapping cost, quality, and latency trade‑offs for Qwen2.5‑7B‑Instruct on L4, A100, and H100 GPUs. Using 54 measured configurations and a calibrated simulator, it identifies 18 of 36 setups on the Pareto frontier, showing that combined methods outperform single ones. Quality tests reveal that AWQ 4bit and FP8 weights offer significant latency reductions while largely preserving accuracy, but naive FP8 KV caching fails to answer any questions correctly.
arXiv:2606. 24033v1 Announce Type: new Abstract: Existing low-bit KV-cache quantizers often treat each cached key as a flat vector.
arXiv:2606. 29733v1 Announce Type: cross Abstract: Organizations that cannot send data to a cloud API increasingly ask: how good is Text-to-SQL if the model must run on-premises on open weights, and which popular accuracy "recipes" are worth their compute?
Organizations that cannot send data to a cloud API increasingly ask: how good is Text-to-SQL if the model must run on-premises on open weights, and which popular accuracy "recipes" are worth their compute? We answer with an honest, fully reproducible benchmark on the BIRD development split (n=1534, Execution Accuracy), evaluating three open model families across two generations -- Qwen2.
arXiv:2606. 08051v1 Announce Type: new Abstract: Financial transaction processing requires extracting structured merchant information from noisy, abbreviated bank transaction strings at scale.
The paper evaluates how different design choices—document feeding strategy, retrieval method, and execution mode—affect Vision‑Language Models (VLMs) on long‑document question answering. Experiments on two benchmarks show that a multi‑tool agent only outperforms static input when the VLM is large, that retrieval modality (image vs text) is more critical than the specific retriever, and that combining the best pipelines per question can significantly boost performance. The study highlights the trade‑offs between token efficiency, model size, and pipeline complexity for deploying VLMs on complex documents.