DeepSeek open-sourced DeepInfer, the offline inference engine behind its own V4.1-Flash
AspireAI community · DeepSeek on GitHub
DeepSeek released DeepInfer under Apache 2.0, calling it the high-performance inference framework that powers its large-scale production services. The practical scope is narrower than the headline suggests.
DeepInfer was derived from the open-source vLLM framework and then rebuilt bottom-up — scheduling, preprocessing and sampling rewritten in C++ in the repository (17.6k stars at release). It covers offline inference only, specialised to DeepSeek's own V4.1-Flash. It is not a general-purpose deployment framework, and the README explicitly notes three pieces required for a complete inference service that are not in this release: a KV cache system, VE/prefill/decode disaggregation, and load balancing across data-parallel replicas for both prefill and decode.
Underneath, DeepInfer leans on TileLang custom operators, sparse mixture-of-experts kernels (DeepEP), speculative decoding via DSpark and confidence-scheduled verification, and decoder SWA bounded replay — the same architectural patterns that have been quietly spreading across large-serving stacks in 2026. Hardware support is limited to NVIDIA SM100 GPUs and Huawei Ascend 950 NPUs.
Read the story and explore more from the AspireAI community.
Two critical PHP remote code execution flaws — one found by GPT-5.6 Sol — were patched on October 21, 2026, and OpenAI published a disclosure framework alongside the fix. Fixed versions: PHP 8.5.12, 8.4.27, 8.3.36 and 8.2.35. Both allow unauthenticated remote code execution, and PHP's advisory says risk is highest for mod_php, where a demonstrated exploit triggers before any application code runs. The CVEs are distinct failure modes. CVE-2026-109618 (OOM corruption): out-of-memory handling can interrupt PHP while internal request data is only partially initialized, and request cleanup may then treat the invalid data as valid. CVE-2026-109619 (stale global state): request-owned internal state can survive after its backing memory is freed, and a later request served by the same worker may use that stale state. OpenAI states GPT-5.6 Sol identified the first flaw through its Patch the Planet initiative, and that Wiz independently discovered and reported both vulnerabilities. PHP's maintainers led the fixes and release, with Wiz, Cloudflare and OpenAI contributing research and coordination. Wiz's write-up adds that it used GPT-5.6 Sol and Gemini 4 Argon throughout, with Gemini 4 Argon contributing to finding the vulnerability and validating the patch. OpenAI describes the gap between discovery and public exploitation as a "Defender's Window," proposes a five-stage response framework, and committed $1 billion in subsidised Daybreak model access for organizations with limited security resources. Honest caveats: these are OpenAI's and Wiz's own characterizations, and OpenAI also notes the same capabilities help attackers build offensive tooling faster. PHP 8.1 and older no longer receive updates from the PHP project.