--- title: DeepSeek just open-sourced its inference engine | daily.dev description: DeepInfer is DeepSeek's open-sourced high-performance inference framework used internally for large-scale production serving of DeepSeek models, starting with... canonical: https://daily.dev/posts/deepseek-just-open-sourced-its-inference-engine-ozv0insdt twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: DeepSeek just open-sourced its inference engine | daily.dev og:description: DeepInfer is DeepSeek's open-sourced high-performance inference framework used internally for large-scale production serving of DeepSeek models, starting with... og:url: https://daily.dev/posts/deepseek-just-open-sourced-its-inference-engine-ozv0insdt og:image: https://api.daily.dev/og/posts/OZV0iNsdt.png og:image:alt: DeepSeek just open-sourced its inference engine og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # DeepSeek just open-sourced its inference engine **[Hacker News](https://daily.dev/sources/hn)** · 3 min read · 0 upvotes · 0 comments ## Summary DeepInfer is DeepSeek's open-sourced high-performance inference framework used internally for large-scale production serving of DeepSeek models, starting with DeepSeek-V4.1-Flash. It offers offline inference with optimized kernels (FlashMLA, DeepGEMM, DeepEP, TileKernels, DeepSelect), advanced parallelism (attention DP, balanced CP, MoE EP+EPLB), speculative decoding via DSpark, bounded SWA replay, async batch scheduling, batch-invariant inference, deterministic sampling, and structured outputs. It supports NVIDIA SM100 GPUs and Huawei Ascend 950 NPUs, requires Linux, GCC 13+, Python 3.12, and CUDA 13 or CANN 9.2. A complete production service still needs an external KV cache system, PD disaggregation, and load balancing across replicas. The project is released under Apache 2.0 and builds on vLLM, with inspiration from SGLang and TensorRT-LLM. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What GPUs and NPUs does DeepInfer support for running DeepSeek models? DeepInfer supports NVIDIA SM100 GPUs and Huawei Ascend 950 NPUs. It requires Linux, GCC 13.0 or higher, Python 3.12, and either CUDA 13 for NVIDIA hardware or CANN 9.2 for Ascend hardware. The accelerator target is set via the DEEPINFER_ACCELERATOR environment variable before building from source with build.sh. _Teams evaluating inference hardware for DeepSeek deployments can track framework updates on daily.dev._ ### How do I get deterministic, reproducible outputs from a DeepSeek model with DeepInfer? Set DEEPINFER_BATCH_INVARIANT=1 and DEEPINFER_ENABLE_MTP_VARLEN=0, then pass a fixed seq_seed to SamplingParams. This produces identical outputs for identical input tokens and sampling parameters, and is currently limited to NVIDIA hardware. Batch-invariant inference alone (DEEPINFER_BATCH_INVARIANT=1) keeps results consistent across different batch compositions. _Developers debugging nondeterministic LLM outputs can follow inference framework tips on daily.dev._ ### What is missing from DeepInfer to run a complete production LLM inference service? The open-source release omits a KV cache system, prefill/decode disaggregation across virtual engines, and load balancing across data-parallel replicas for both prefill and decode, though most of the engine functionality needed for disaggregation is already implemented. Only offline inference with core serving features is included in this release. _Engineers architecting production LLM serving stacks can compare framework gaps on daily.dev._ ## Community take How the wider developer community reacted, aggregated from 1 discussion and 213 comments across hackernews (as of 2026-10-20). **TL;DR:** Discussion centers less on the technical release itself and more on its geopolitical and economic implications — whether open-sourcing DeepSeek's inference stack undermines the moat and valuations of US frontier labs, with heavy debate on profitability, enterprise adoption of Chinese models, and motives behind the release. **Sentiment:** 40% positive · 35% mixed · 25% skeptical **The case for** - Many argue this accelerates commoditization of inference, driving down costs and benefiting users/enterprises regardless of who built it. - Some see it as evidence that inference is highly profitable, with cited figures suggesting strong margins even at off-peak pricing. - Several commenters say enterprises (including in Europe) are already considering or adopting Chinese open models for cost and sovereignty reasons. **The pushback** - Skeptics question whether big corporations will actually trust and deploy Chinese-origin models due to security, regulatory, and adversarial-payload concerns. - Some doubt the release meaningfully threatens OpenAI/Anthropic's moat, noting those labs' advantages still include enterprise contracts, hardware access, and data. - Others suspect strategic/geopolitical motives behind the open-sourcing (undermining US AI valuations) rather than pure altruism or open-source spirit. **By community** - hackernews (heated): Debate sprawls across geopolitics, whether this erodes US AI labs' moats, inference profitability economics, and skepticism about enterprise adoption of Chinese models, with sharp disagreement throughout. **Hottest debate:** Whether open-sourcing this stack genuinely threatens the valuations/moats of OpenAI and Anthropic, or whether enterprise security and regulatory concerns will keep Chinese-origin models out of serious business use regardless. **Open questions** - Why would DeepSeek give up trade secrets that seem to keep getting absorbed by competitors like Anthropic/OpenAI? - Does the quoted $38/card/hour figure represent real profit after accounting for full infrastructure costs, or just revenue? - Will regulatory/security concerns actually stop large enterprises from adopting open Chinese models at scale? **Highlights** > I've been trying to find an answer to that, too. The best I've got right now is this: Moat-like things going for them: - access to the US government (for huge inflated government contracts as a source of free capital, having the competition banned, having their products legally mandated, getting other preferential treatment, having foreign governments bullied into granting similar advantages) Too unsustainable, too fragile, too small: - Strong brands: Brand loyalty seems like a pretty insignificant factor in AI right now - Semi-exclusive hardware access, RAM buyouts: Unsustainable even in the short term - Lock-in effects: Their models aren't very stable across versions, or very unique, and switching providers is about as easy as it can be in a highly competitive market. - Exclusive technology that is important, advanced and hard to replicate to a degree that would materially set them apart and justify potentially much higher cost. Maybe I'm missing something here, but a lot of the claims they make to that end fall apart even on light scrutiny (due to things like test sets that are small, hand-picked and clearly overfitted on, or broad general claims that cannot be substantiated). I'm getting the feeling they don't have anything that materially sets them apart at all, but that's seems impossible to measure in any meaningful way, so who knows, they might have something here. > — [dividedbyzero on hackernews](https://news.ycombinator.com/item?id=50164580) > A nuclear bomb "Based on this framework, we have achieved high-throughput, low-latency large-scale inference services for DeepSeek V4.1 Flash. Currently, the service throughput of a single cluster is 155 trillion tokens/day, and the overall revenue is $38 per card per hour (at off-peak pricing)" Source: https://zhuanlan.zhihu.com/p/2095560295930508953 > — [schneehertz on hackernews · 6 comments](https://news.ycombinator.com/item?id=50163494) > This isn't true, especially not with the inference engine becoming public, now you can build your on models on the same or similar architecture and ship massive gains on top of these stacks. I think people don't realize the Salesforce SAP Palantir would love to ship these models, and they have/are shipping them. The threat of exfilteration of data via these models is high but it's nowhere near as high as the margins. For instance if you could cut your ai input bill by over 90% would you do it? Can you put some of that extra margin say 10-20% to make it more secure. I know of atleast 10 fortune 500 companies that are entirely planning to or have moved to Chinese models for a large portion of their work. It's insane people in finance are delusional enough to think that won't happen. Maybe Govt will try to de-risk with bans on using open models but I don't think that's going to work at scale, people will literally spawn labs to launder DeepSeek/GLM models into a US model by some novel training etc approach or something. I still don't think that it's as much a kami-kaze rather it's an attempt to normalize the world around the Chinese stack. If DeepInfer is supported by everyone, it will be much easier to export stuff aka hardware that only supports it for now or is optimized for it. Assume china starts selling hyper optimized Asics for inference at some point. This feels like a race to the bottom as soon as possible because they have much lower costs, if there is a Wipeout in AI Labs in US chinese labs are largely insulated, and they can hopefully buy Nvidia chips for cheap if that does happen. > — [minraws on hackernews](https://news.ycombinator.com/item?id=50164528) > I'm wondering how it benefits Deepseek. Why would they willingly give up their trade secrets? It's obviously very valuable, as they are running a profitable company. It follows the same trend as when they released their cache optimizations a few months back: why do it? What followed their release of this technology was that Anthropic and OpenAI silently released models which were on-par or similarly intelligent, but "surprisingly" had much cheaper cached tokens. So their inventions were obviously just worked into their competitors, who just got much greater margins + became more profitable. The same thing goes here: I'm sure there are inventions and optimizations which are unknown to Deepseeks competitors which yet again will be worked in. So once again, they're letting their trade secrets go. My question is: why? How does Deepseek benefit from this? There must be some gain I'm not seeing as they keep doing this play over and over, and I doubt it's "for the good of open source", as China is practically as isolated as you can get. To believe that this is in the spirit of the open source community is heavily naive. > — [baalimago on hackernews · 3 comments](https://news.ycombinator.com/item?id=50163908) > I saw the same kind of comments when the first Deepseek model was initially released. However the relevance that investors assign to something like this does not seem to match the excitement expressed here. I think they do not believe that big corporations in the US or Europe would actually use chinese models in their business operations due to security, regulatory and/or business continuity concerns. > — [bonplan23 on hackernews · 11 comments](https://news.ycombinator.com/item?id=50164066) **Source threads** - [hackernews](https://news.ycombinator.com/item?id=50163277) · 524 points · 213 comments ## Similar posts on daily.dev - [DeepSeek-V4.1-Flash on vLLM: 5x Agentic Throughput Since Day 0](https://daily.dev/posts/deepseek-v4-1-flash-on-vllm-5x-agentic-throughput-since-day-0-js5lna7tm) · vLLM · 0 upvotes · 0 comments - [GitHub - antirez/ds4: DeepSeek 4 Flash local inference engine for Metal](https://daily.dev/posts/github---antirez-ds4-deepseek-4-flash-local-inference-engine-for-metal-sqcj9sya5) · Hacker News · 3 upvotes · 0 comments - [DSpark: the DeepSeek inference upgrade that matters more than most model launches](https://daily.dev/posts/dspark-the-deepseek-inference-upgrade-that-matters-more-than-most-model-launches-teogimjdi) · Medium · 1 upvotes · 0 comments --- Tags: [#python](https://daily.dev/tags/python), [#gpu](https://daily.dev/tags/gpu), [#ai-inference](https://daily.dev/tags/ai-inference), [#deepseek](https://daily.dev/tags/deepseek), [#vllm](https://daily.dev/tags/vllm) [View this post on daily.dev](https://daily.dev/posts/deepseek-just-open-sourced-its-inference-engine-ozv0insdt) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"DeepSeek just open-sourced its inference engine","url":"https://daily.dev/posts/deepseek-just-open-sourced-its-inference-engine-ozv0insdt","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/deepseek-just-open-sourced-its-inference-engine-ozv0insdt"},"datePublished":"2026-10-20T10:47:15.468Z","dateModified":"2026-10-20T15:26:06.740Z","description":"DeepInfer is DeepSeek's open-sourced high-performance inference framework used internally for large-scale production serving of DeepSeek models, starting with...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/72455fc63fcad7eb5a443ec8645b7f56?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/72455fc63fcad7eb5a443ec8645b7f56?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Hacker News","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Hacker News","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/hn","url":"https://daily.dev/sources/hn"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/deepseek-just-open-sourced-its-inference-engine-ozv0insdt","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"python,gpu,ai-inference,deepseek,vllm","timeRequired":"PT3M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Hacker News","item":"https://daily.dev/sources/hn"},{"@type":"ListItem","position":3,"name":"DeepSeek just open-sourced its inference engine"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/deepseek-just-open-sourced-its-inference-engine-ozv0insdt#faq","mainEntity":[{"@type":"Question","name":"What GPUs and NPUs does DeepInfer support for running DeepSeek models?","acceptedAnswer":{"@type":"Answer","text":"DeepInfer supports NVIDIA SM100 GPUs and Huawei Ascend 950 NPUs. It requires Linux, GCC 13.0 or higher, Python 3.12, and either CUDA 13 for NVIDIA hardware or CANN 9.2 for Ascend hardware. The accelerator target is set via the DEEPINFER_ACCELERATOR environment variable before building from source with build.sh. Teams evaluating inference hardware for DeepSeek deployments can track framework updates on daily.dev."}},{"@type":"Question","name":"How do I get deterministic, reproducible outputs from a DeepSeek model with DeepInfer?","acceptedAnswer":{"@type":"Answer","text":"Set DEEPINFER_BATCH_INVARIANT=1 and DEEPINFER_ENABLE_MTP_VARLEN=0, then pass a fixed seq_seed to SamplingParams. This produces identical outputs for identical input tokens and sampling parameters, and is currently limited to NVIDIA hardware. Batch-invariant inference alone (DEEPINFER_BATCH_INVARIANT=1) keeps results consistent across different batch compositions. Developers debugging nondeterministic LLM outputs can follow inference framework tips on daily.dev."}},{"@type":"Question","name":"What is missing from DeepInfer to run a complete production LLM inference service?","acceptedAnswer":{"@type":"Answer","text":"The open-source release omits a KV cache system, prefill/decode disaggregation across virtual engines, and load balancing across data-parallel replicas for both prefill and decode, though most of the engine functionality needed for disaggregation is already implemented. Only offline inference with core serving features is included in this release. Engineers architecting production LLM serving stacks can compare framework gaps on daily.dev."}}]} ```