AI Coding Live News

DeepSeek officially open-sourced DeepInfer under Apache 2.0, its production-grade inference engine serving DeepSeek-V4.1-Flash at scale. Originating from vLLM with architectural refinements from SGLang and TensorRT-LLM, DeepInfer natively targets NVIDIA SM100 GPUs and Huawei Ascend 950 NPUs. It integrates specialized kernels including FlashMLA, DeepGEMM, DeepEP, and TileKernels. The engine features DSpark confidence-scheduled speculative decoding with 5-token drafts, SWA bounded replay over a 140-token sliding window, and balanced MoE expert parallelism. DeepSeek simultaneously open-sourced deepseek-recipe, delivering an end-to-end open ecosystem across models, kernels, and inference runtimes.

Zoom

On Oct 20 (UTC) DeepSeek open-sourced DeepInfer (Apache 2.0), the in-house inference stack that serves DeepSeek-V4.1-Flash at scale. The release covers offline inference with Attention DP/CP and MoE EP+EPLB parallelism, DSpark speculative decoding, SWA bounded replay, batch-invariant inference, deterministic sampling and structured outputs on NVIDIA SM100 GPUs and Huawei Ascend 950 NPUs. The KV cache system, prefill/decode disaggregation and load balancing are not included. DeepSeek also released deepseek-recipe (MIT), which converts Chat Completions, Messages and Responses requests and encodes them the same way the official API does.

Zoom

The SGLang team released v0.5.22 featuring 950 PRs from 245 contributors: DeepSeek-V4.1 delivers up to 2.3x more throughput per GPU on NVIDIA H200 and 1.9x on AMD MI350X/MI355X via DSpark. The new InstantTensor loader cuts model loading time by 10x. B200 decodes Qwen3.8-Flash-Next 12% faster, while B300 speeds up GLM-5.3-Flash by 10% and yields 1.85x decode throughput for MiMo-V2.6-Pro. SGLang also adds native Apple Silicon PyTorch support and ComfyUI integration.

Zoom

vLLM and NVIDIA unveiled a unified CuTe DSL decode megakernel (~12,000 LoC authored by NVIDIA CentML's Benjamin Chislett) for Moonshot AI's frontier Kimi K3 model on NVIDIA GB300 NVL72. By fusing attention, MoE, and cross-GPU communication, the optimization cuts per-layer latency from 130 µs (23 kernels) to 69 µs (13 kernels), delivering 842 tokens/s at batch=1 with DSpark speculative decoding (1.73x faster than stock vLLM) and up to 1.8x higher P90 per-user interactivity (403.2–423 tok/s/user) on SemiAnalysis AgentX, with DeepSeek-V4.1-Flash (PR #61868) and GLM-5.3 support coming next.

Zoom

A vLLM blog post by NVIDIA engineer Benjamin Chislett details an agent-assisted CuTe DSL decode path for Kimi K3 on NVIDIA GB300 that fuses attention, MoE and NVLink communication, cutting per-layer time from 130 µs across 23 kernels to 69 µs across 13. With DSpark speculative decoding on 16 GPUs it reaches 842 tok/s at batch 1, 1.73x stock vLLM; PR #61867 was merged on Oct 16.

Zoom

On 2026-10-12 OpenBMB released MiniCPM-V 4.7, an Apache-2.0 open multimodal family with a 35B-A3B variant (the series' first MoE) and a 1B variant. Its Lookahead Expert Scheduling (LES) prefetches experts across layers and, combined with layer-wise mixed-precision quantization and DSpark speculative sampling, lifts SSD-offloaded decoding on an iPad Pro M4 (16GB) from 2.97 to 17.39 tokens/s (5.86x), per OpenBMB. Weights are on Hugging Face, ModelScope and Ollama, with vLLM, SGLang, llama.cpp and iOS/Android/HarmonyOS support.

Zoom

Inferact open-sourced inferact/tpu-megakernels on 2026-09-23: a Pallas megakernel collection for TPU v7. Their blog reports Kimi K3 at 709 tok/s on 16× TPU v7 Ironwood vs 452 tok/s on 16× GB200 under DSpark speculative decoding (acceptance length 6), and roughly 1.4–2× the GB200 baseline at batch sizes 1–8 without speculation. All 92 MoE layers of Kimi K3 run in a single kernel with cross-layer weight prefetch.

Zoom