AI Coding Live News

On November 5 Ant Group’s Ant Ling (@AntLingAGI) launched Ling-3.2-flash: a 560B-total / 25B-active native multimodal MoE with a 1M context window and native image, text and video input. The official changelog targets complex visual understanding, multimodal long-horizon agents, 3D understanding and interaction, and medical multimodal work; APIs are OpenAI- and Anthropic-compatible and free for the first two weeks. The launch post cites vendor evals versus Claude Opus 5 (max): OmniDocBench1.5 92.21 vs 90.56, ZEROBench(Sub) 43.71 vs 39.52, Vision2Web 85.86 vs 80.20. DesignArena placed it about #10 on Image-to-Frontend with Elo 1238.

Zoom

The vLLM project team and Ant Group officially open-sourced Humming (humming-kernels), a specialized high-performance kernel library designed for serving quantized MoE and dense LLMs at massive scale. Humming natively supports WnA16, W8A8, W4A8, and W4A4 across INT1–INT8 and FP4–FP8 formats, spanning NVIDIA architectures from Turing through Blackwell as well as T-Head Zhenwu 810E silicon. In production benchmarks, Humming kernels outpace cuBLAS by 3–4x at small batch sizes and surpass Marlin by 2x on H200 clusters. Serving DeepSeek-V4.1-Flash across 8x H20 GPUs, Humming drives a +43.3% throughput gain under 64 concurrent requests while reducing time-to-first-token (TTFT) by 32%, pre-integrated directly into vLLM v0.29.0+.

Zoom

On Oct 21 the vLLM community and Ant Group open-sourced Humming (Apache 2.0), a quantized-inference library that JIT-compiles GEMM kernels on demand. It supports every NVIDIA architecture from Turing on plus T-Head's Zhenwu 810E, and covers weight and activation combinations from INT1-INT8 and FP4-FP8 for dense and MoE workloads. In vLLM's microbenchmarks it runs 2-5x faster than vLLM Marlin, FlashInfer or DeepGEMM in some cases; on 8 H20 GPUs, switching DeepSeek-V4.1-Flash MoE from Marlin W4A16 to Humming W4A8 raised throughput 14-43%. vLLM 0.29.0 ships it built in.

Zoom

In the latest independent Text-to-Speech (TTS) evaluations published by Artificial Analysis, Ant Group's open-source Ming-3.0-tts achieved a 93.2% pronunciation accuracy score, ranking #1 among all 31 evaluated models (outperforming commercial leader ElevenLabs v4 at 91.7%). Offering both a dense 0.5B parameter variant and a 7.9B mixture-of-experts (MoE) model, it delivers voice cloning and preset voices with a Controlled Voice Elo score of 1,069 (#1 among open-weight models), fully released under the permissive MIT license.

Zoom

On 2026-09-30 InclusionAI (Ant Group) announced Ling-3.1-flash: ~560B total / ~25B active MoE hybrid-reasoning model, designed for up to 1M context (trial/gateway routes often expose 256K–262K). Weights are not on Hugging Face yet. Vercel AI Gateway and OpenCode Zen list limited-time free access (~through 2026-10-13). Vendor-reported scores include SWE-Pro 65.39, Terminal-Bench 4.0 40.40, CyberGym 87.90—not independently reproduced.

Zoom

Deploying 70B+ LLMs under tight memory constraints necessitates extreme 4-bit weight, activation, and KV-cache quantization (W4A4KV4). However, current methods predominantly focus on suppressing activation outliers, overlooking their geometric alignment with the quantizer grid. Researchers introduce PrismQuant, a quantizer-aware rotation framework that mathematically aligns the leading activation eigenspace with the constant group subspace of asymmetric grouped INT4 quantization. Formulated as a Ky Fan trace maximization problem, PrismQuant derives a closed-form, provably optimal rotation solution without requiring expensive gradient descent. Benchmarked across Llama, Qwen, and Mistral architectures up to 70B parameters and 30B MoE variants, PrismQuant sets new SOTA marks: on Llama-3.1-70B under W4A4KV4, it achieves 72.46% zero-shot accuracy—merely 0.22 percentage points below full FP16 precision. Deployment benchmarks demonstrate a 1.51x prefill speedup and 56.34% reduction in peak decoding VRAM with code open-sourced on GitHub.

Zoom