AI Coding Live News

On Oct 28, Mixpanel founder Suhail Doshi announced his new company Particle on X, with its first model, Particle-1, live now. Particle's blog says it is a reinforcement-learning post-train of DeepSeek V4.1 Flash that uses 28.4% to 52.2% fewer output tokens and costs 34.4% to 51.6% less per task across four coding and data engineering benchmarks, with pass rates inside the base model's confidence intervals. It is available through the Particle API, OpenRouter and Vercel AI Gateway; Particle's docs list $0.25 input and $1.00 output per million tokens with a 1,048,576-token context window.

Zoom

Cursor announced on Oct 26 (UTC) that DeepSeek V4.1 Flash is now available in Cursor and can be turned on under Cursor Settings > Models. Cursor says every effort level sits on the CursorBench cost frontier, from $0.60 to $0.98 per task, with no model scoring higher at those prices. The official CursorBench 4.0 leaderboard lists DeepSeek V4.1 Flash 1017 at 47.7% on Max ($0.98 per task), 46.3% on Medium ($0.80), 45.6% on High ($0.77) and 44.9% on Low ($0.60). The top score on the board, Opus 5.5 Max, is 57.8% but costs $13.43 per task.

Zoom

Independent AI evaluation platform Artificial Analysis (@ArtificialAnlys) officially benchmarked DeepSeek's web search API (DeepSeek Search). Augmenting the base model with DeepSeek Search boosted its Search Index score from 33 to 69—an impressive +36 point leap (ranking 17th among 27 tested search APIs). DeepSeek Search established a market-leading price-performance ratio, priced at just $0.75 per 1,000 searches (~$0.032 per completed task), making it the most cost-effective paid search API evaluated. It recorded 70% accuracy on AA-Omniscience and 63% on BrowseComp, highlighting an optimal balance between factual grounding and operational economics.

Zoom

LMSYS Org in collaboration with the NVIDIA Dynamo team officially unveiled Elastic Expert Parallelism (Elastic EP) with NIXL backend integration in SGLang (@lmsysorg). Addressing the critical vulnerability of large-scale MoE deployments (such as DeepSeek-V3/V4) where static EP causes entire cluster crashes upon single-node failures and prevents live capacity resizing, Elastic EP decouples rigid expert-to-GPU bindings. Leveraging NVIDIA NIXL device APIs and Mooncake orchestrators, SGLang enables live scaling of active MoE serving deployments (e.g. dynamically expanding from 20 to 24 GPUs) without draining traffic or restarting clusters, while delivering resilient fault tolerance.

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

Hours after DeepSeek open-sourced DeepInfer, the vLLM project team released official benchmark parity data serving DeepSeek-V4.1-Flash. Utilizing DeepSeek's identical decoding setup (131K context window, nextn=3 speculative decoding), vLLM closed its throughput performance delta to within 6% of DeepInfer across batch sizes 8 through 256 on NVIDIA GB200 systems. On GB300 hardware, vLLM attained up to 1,000,000 tokens/second per GPU and 826 tokens/second per user, generating $38.96 in hourly GPU revenue at DeepSeek off-peak rates. vLLM simultaneously shipped day-0 runtime support for FastH3-Omni and Spark-X2.6-4B.

Zoom

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

On Oct 19 (UTC) Unsloth released dynamic GGUF quants and a run-locally guide for DeepSeek-V4.1-Flash-1017. Per Unsloth, the 1-bit UD-IQ1_M quant is 250.4 GB (vs 508.4 GB for lossless Q8), keeps 88.2% top-1 agreement with the official weights on long17k, and runs on 128 GB+ RAM machines, because the model's 110.6–202.8 GB Engram n-gram table can stay on SSD via mmap. Running it currently requires Unsloth's llama.cpp PR build or Unsloth Desktop.

Zoom

Researchers introduced BlenderWorld (arXiv:2610.23986), the first comprehensive benchmark evaluating visual agents creating and editing 3D models from real-world references in Blender. Spanning 223 tasks across procedural geometry, Python scripting, material shaders, spatial layouts, and lighting, GPT-6 Astra leads the benchmark with a composite Score of 79.9 (and a 42.2% Perfect completion rate), followed by Opus-5 at 73.0. Open-weight flagship DeepSeek-V4.1-Flash claims 65.7, matching proprietary models while relying on active execution-and-inspection tool loops.

Zoom

On October 19 independent evaluator Artificial Analysis launched two health-conversation leaderboards built on OpenAI's HealthBench (5,000 realistic health conversations) and HealthBench Professional (525 clinician conversations), graded against physician-written rubrics and reported as both raw and OpenAI-style length-adjusted scores. On Professional, GPT-6 Astra (max) leads at 66.0% length-adjusted, ahead of GPT-6.1 Sol (65.1%) and Claude Sonnet 5.5 (63.0%); Claude Opus 5.5 has the top raw score (71.4%) but drops to sixth (59.9%) because its ~5,900-character answers are penalized. On HealthBench, Claude Sonnet 5.5 leads at 62.1%, with DeepSeek V4.1 Flash close behind at 60.9% for about 1/16 of the cost per task.

Zoom