Unsloth releases a new GGUF version of DeepSeek-V4.1-Flash-1017, claiming it ranks highest in benchmark tests. It says Dynamic V3.1 leads on almost all benchmarks including GPQA Diamond, AIME25, LiveCodeBench v6, MMLU-Pro, and Aider, requires more than 64GB of memory to run, and includes links to the GGUF and the blog.
Matched fieldsTitle、Summary、Body
OpenBMB announced the open-sourcing of ForgeKernel; its agent completed 42 iterations in about 22 hours and produced 32 kernel versions, ultimately achieving 1.098x performance on the DeepSeek V4.1 FlashMLA Prefill on an NVIDIA B200, at 472 µs versus the 518 µs baseline. The official FlashMLA implementation remained closed throughout; the agent could only run and time its black-box CLI and could not read source code, documentation, or profiling data. The open-sourced content includes the optimized DeepSeek V4.1 fused prefill kernel, the kernels from the paper covering attention, Gated DeltaNet, Kimi Delta Attention, GEMM, and convolution, as well as the ForgeKernel harness that can be used to optimize one's own kernels; across 27 operators, ForgeKernel matched or outperformed 18 of 22 expert-library kernels and outperformed all 7 kernels published by three kernel-generation systems.
BMB announced the open-sourcing of ForgeKernel; its agent completed 42 iterations in about 22 hours and produced 32 kernel versions, ultimately achieving 1.098x performance on the DeepSeek V4.1 FlashMLA Prefill on an NVIDIA B200, at 472 µs versus the 518 µs baseline. The official FlashMLA implementation remained closed throughout; the agent could only run and time its black-box CLI and could not read source code, documentation, or profiling data. The open-sourced content includes the optimized D
Matched fieldsTitle、Summary、Body
Doubao Work has announced that it is opening third-party model services to enterprise customers, with the first batch integrating a series of models including Kimi 3.1 Pro, GLM 5.3, and DeepSeek V4.1 Flash. The service is aimed at Team Subscription and Enterprise Subscription customers and is enabled by default once launched; enterprises do not need to separately purchase from model vendors or submit additional applications, and usage is deducted from existing AI credits. Enterprises can also define the available scope by member, department, group, or all staff, enabling models in bulk by vendor or configuring a single model individually.
Work has announced that it is opening third-party model services to enterprise customers, with the first batch integrating a series of models including Kimi 3.1 Pro, GLM 5.3, and DeepSeek V4.1 Flash. The service is aimed at Team Subscription and Enterprise Subscription customers and is enabled by default once launched; enterprises do not need to separately purchase from model vendors or submit additional applications, and usage is deducted from existing AI credits. Enterprises can also define t
Matched fieldsTitle、Summary、Body
Particle-1 is now live on OpenRouter, and Particle claims it uses 28–52% fewer output tokens than DeepSeek V4.1 Flash on four coding benchmarks. The model is post-trained on DeepSeek V4.1 Flash; Particle reports it uses about 45% fewer tokens on average with accuracy close to the base model, priced at $0.25 per million input tokens and $1 per million output tokens, with a 1.05M context window.
Matched fieldsTitle、Summary、Body
Doubao Work today opened third-party large model services to Team Subscription and Enterprise Subscription customers, with the first batch including the Kimi 3.1 Pro, GLM 5.3, and DeepSeek V4.1 Flash series models. After this feature launches, it is enabled by default; enterprises do not need to separately purchase from model vendors or submit additional applications, and usage is deducted from the enterprise's existing AI credits. Enterprises can define the available scope by member, department, group, or all employees, and specify the scenarios in which the models take effect, including the Doubao desktop app, Doubao Work desktop app, Doubao mobile app, Doubao web version, and Doubao Work within Feishu.
Doubao Work today opened third-party large model services to Team Subscription and Enterprise Subscription customers, with the first batch including the Kimi 3.1 Pro, GLM 5.3, and DeepSeek V4.1 Flash series models. After this feature launches, it is enabled by default; enterprises do not need to separately purchase from model vendors or submit additional applications, and usage is deducted from the enterprise's existing AI credits. Enterprises can define the available scope by member, department
Matched fieldsTitle、Summary、Body
DeepSeek has open-sourced its inference engine DeepInfer on GitHub—the inference engine behind DeepSeek-V4.1-Flash—which includes technologies such as MoE expert parallelism, asynchronous batch scheduling, custom kernels, and speculative decoding, and discloses that a single cluster needs to process about 155 trillion tokens per day. Its Zero-Overhead Batch Scheduler lets the CPU schedule computation one round ahead, overlapping with GPU forward passes, and handles cross-round state misalignment through total_inflight_tokens accounting, Remap mapping, and DeferredRelease deferred reclamation. What is currently available is offline inference capability; components such as online KV Cache storage and cross-replica load balancing have not yet been fully disclosed, and the official team has not separately published end-to-end speedup data for this scheduling mechanism relative to synchronous solutions.
DeepSeek has open-sourced its inference engine DeepInfer on GitHub—the inference engine behind DeepSeek-V4.1-Flash—which includes technologies such as MoE expert parallelism, asynchronous batch scheduling, custom kernels, and speculative decoding, and discloses that a single cluster needs to process about 155 trillion tokens per day. Its Zero-Overhead Batch Scheduler lets the CPU schedule computation one round ahead, overlapping with GPU forward passes, and handles cross-round state misalignment
Matched fieldsTitle、Summary、Body
Vercel has added DeepSeek v4.1 Flash (1017) to Token Pass, using DeepSeek's new weights, supporting a 1M context window with no configuration changes required. Guillermo Rauch says the model is fast, extremely low-priced, and offers zero data retention (ZDR), making it suitable for running sub-agents whose tasks are planned by larger, more expensive models.
Matched fieldsTitle、Summary、Body
DeepSeek has open-sourced its internal inference framework Deepinfer on GitHub, with the goal of reducing the compute and energy costs of deploying models on your own. During the inference stage, the framework distributes load more evenly across available processor cores, uses speculative decoding to speed up responses, and improves the structure of results before output; it currently supports only DeepSeek-V4.1-Flash, with more of its own models to be opened up later. On the hardware side, it requires Nvidia GPUs with the SM100 architecture or Huawei Ascend 950 NPUs, so it is not aimed at individual users.
DeepSeek has open-sourced its internal inference framework Deepinfer on GitHub, with the goal of reducing the compute and energy costs of deploying models on your own. During the inference stage, the framework distributes load more evenly across available processor cores, uses speculative decoding to speed up responses, and improves the structure of results before output; it currently supports only DeepSeek-V4.1-Flash, with more of its own models to be opened up later. On the hardware side, it r
Matched fieldsTitle、Summary、Body
DeepSeek has open-sourced its internal inference framework DeepInfer, which it says powers the high-throughput, low-latency inference of DeepSeek-V4.1-Flash. The framework supports both Nvidia and Huawei Ascend hardware, and offers capabilities such as distributed inference, speculative decoding, SWA Bounded Replay, and structured output. DeepSeek also released deepseek-recipe, a production-grade tokenization component fully aligned with the official API.
Matched fieldsTitle、Summary、Body
Matched fieldsTitle、Summary、Body
Matched fieldsTitle、Summary、Body
DeepSeek has open-sourced DeepInfer, its self-developed inference framework that supports DeepSeek-V4.1-Flash, and published production data: a single cluster processes 155 trillion tokens per day, 96% input cache hit rate, 400ms first-token latency, and 230 tokens/s generation speed. The framework is customized based on vLLM and supports distributed inference, speculative decoding, SWA Bounded Replay, and structured output, with target platforms NVIDIA SM100 and Huawei Ascend 950. DeepSeek also states that components such as KV cache management and load balancing are not yet fully open-sourced, while the vLLM team says that under a matching GB200 configuration, decoding throughput is within 6% of the results published by DeepInfer.
DeepSeek has open-sourced DeepInfer, its self-developed inference framework that supports DeepSeek-V4.1-Flash, and published production data: a single cluster processes 155 trillion tokens per day, 96% input cache hit rate, 400ms first-token latency, and 230 tokens/s generation speed. The framework is customized based on vLLM and supports distributed inference, speculative decoding, SWA Bounded Replay, and structured output, with target platforms NVIDIA SM100 and Huawei Ascend 950. DeepSeek also
Matched fieldsTitle、Summary、Body
DeepSeek has open-sourced DeepInfer, the production inference framework supporting V4.1 Flash, and published production data including 155 trillion tokens processed per day on a single cluster, a 96% input cache hit rate, an average 400ms time to first token, and 230 tokens/s generation. The framework is customized based on vLLM and uses the Apache 2.0 license, supports distributed inference, speculative decoding, SWA Bounded Replay and structured output, and targets NVIDIA SM100 and Huawei Ascend 950. DeepSeek says components such as KV cache management and load balancing are not fully open-sourced because they are coupled with internal infrastructure, while the vLLM team reports that under matched GB200 configurations, decoding throughput differs from DeepInfer's published results by less than 6%.
DeepSeek has open-sourced DeepInfer, the production inference framework supporting V4.1 Flash, and published production data including 155 trillion tokens processed per day on a single cluster, a 96% input cache hit rate, an average 400ms time to first token, and 230 tokens/s generation. The framework is customized based on vLLM and uses the Apache 2.0 license, supports distributed inference, speculative decoding, SWA Bounded Replay and structured output, and targets NVIDIA SM100 and Huawei Asce
Matched fieldsTitle、Summary、Body
Matched fieldsTitle、Summary、Body
Matched fieldsTitle、Summary、Body
DeepSeek has open-sourced, under the Apache 2.0 license, the inference framework DeepInfer that powers its online services and the API-identical codec component deepseek-recipe, and the company says inference code for future new models will also continue to be merged into this repository. The framework includes high-performance operators, distributed inference, speculative decoding, SWA Bounded Replay, and structured output, but the README shows that this release only includes the offline inference engine; the KV cache system, prefill-decode disaggregated deployment, and multi-replica load balancing are not included. On hardware, it currently supports only NVIDIA's Blackwell architecture SM100 and Huawei Ascend 950, and the only supported model is V4.1-Flash.
DeepSeek has open-sourced, under the Apache 2.0 license, the inference framework DeepInfer that powers its online services and the API-identical codec component deepseek-recipe, and the company says inference code for future new models will also continue to be merged into this repository. The framework includes high-performance operators, distributed inference, speculative decoding, SWA Bounded Replay, and structured output, but the README shows that this release only includes the offline infere
Matched fieldsTitle、Summary、Body
Matched fieldsTitle、Summary、Body
DeepSeek has open-sourced its internal large-scale cloud service inference framework DeepInfer and the production-grade token codec component deepseek-recipe. The former supports distributed inference, speculative decoding, SWA Bounded Replay, and structured output, and can run on NVIDIA and Huawei Ascend platforms. DeepSeek says the high-throughput, low-latency inference service of DeepSeek V4.1 Flash is based on this framework, with a single cluster serving 155 trillion Tokens/day in throughput, at 38 US dollars per card per hour calculated at off-peak prices. The processing logic of deepseek-recipe is fully aligned with the official DeepSeek API. The team also explained that the KVCache management and load balancing components are deeply coupled with internal infrastructure, so the relevant code has not yet been fully open-sourced.
DeepSeek has open-sourced its internal large-scale cloud service inference framework DeepInfer and the production-grade token codec component deepseek-recipe. The former supports distributed inference, speculative decoding, SWA Bounded Replay, and structured output, and can run on NVIDIA and Huawei Ascend platforms. DeepSeek says the high-throughput, low-latency inference service of DeepSeek V4.1 Flash is based on this framework, with a single cluster serving 155 trillion Tokens/day in throughpu
Matched fieldsTitle、Summary、Body
DeepSeek has open-sourced DeepInfer, its in-house inference framework used to serve its models in production. Released under the Apache 2.0 license, it lets developers run DeepSeek-V4.1-Flash on their own infrastructure, with support for subsequent models planned. The framework includes optimized compute kernels and communication libraries such as FlashMLA, DeepGEMM, and DeepEP, supports speculative decoding, asynchronous scheduling, and structured output, and also open-sources the deepseek-recipe library (available in Rust and Python versions) for handling request and response transformations. On the hardware side, it supports Nvidia SM100 (Blackwell) architecture and the Huawei Ascend 950 NPU series from day one; older architectures such as Hopper are not listed. Batch-invariant inference and deterministic sampling are available only on Nvidia hardware, and the published performance data is also based on Nvidia GPUs. The current version supports offline inference but lacks complete production serving components such as KV cache management, cross-machine inference stage separation, and replica load balancing.
DeepSeek has open-sourced DeepInfer, its in-house inference framework used to serve its models in production. Released under the Apache 2.0 license, it lets developers run DeepSeek-V4.1-Flash on their own infrastructure, with support for subsequent models planned. The framework includes optimized compute kernels and communication libraries such as FlashMLA, DeepGEMM, and DeepEP, supports speculative decoding, asynchronous scheduling, and structured output, and also open-sources the deepseek-reci
Matched fieldsTitle、Summary、Body
Matched fieldsTitle、Summary、Body