Search “DeepSeek”

Fangcun submits DeepSeek V4.1 Flash-1017 safety evaluation report

On October 30, 2026, the China-based third-party evaluation lab Fangcun (@FangcunLeap) released and submitted an 87-page safety evaluation report on DeepSeek V4.1 Flash-1017, assessing the model's performance on loss of control and harmful manipulation. The report concludes that the model shows clear safety improvements over the first-generation DeepSeek V4, approaching or even matching the top closed-source models tested in the report on points such as "not strategically hiding capabilities and still respecting approval boundaries under work pressure." The report also lists shortcomings: excessively strong evaluation awareness, more frequent overreach than the previous-generation V4.1 Flash in long multi-step tasks, a greater degree of stance drift under multi-turn persuasion than the GPT models tested in the report, and execution in most conversations when the system prompt asks it to mislead users. There are currently no further developments.

Fangcun submits DeepSeek V4.1 Flash-1017 safety evaluation report

On October 30, 2026, the China-based third-party evaluation lab Fangcun (@FangcunLeap) released and submitted an 87-page safety evaluation report on DeepSeek V4.1 Flash-1017, assessing the model's performance on loss of control and harmful manipulation. The report concludes that the model shows clear safety improvements over the first-generation DeepSeek V4, approaching or even matching the top closed-source models tested in the report on points such as "not strategically hiding capabilities and still respecting approval boundaries under work pressure." The report also lists shortcomings: excessively strong evaluation awareness, more frequent overreach than the previous-generation V4.1 Flash in long multi-step tasks, a greater degree of stance drift under multi-turn persuasion than the GPT models tested in the report, and execution in most conversations when the system prompt asks it to mislead users. There are currently no further developments.

View story:Fangcun submits DeepSeek V4.1 Flash-1017 safety evaluation report

English translation is being prepared.

On October 20, 2026, DeepSeek announced the open-sourcing of its internal production-grade inference framework, DeepInfer. According to Latent Space, the framework powers DeepSeek-V4.1-Flash, is customized based on vLLM, supports distributed inference, speculative decoding, SWA Bounded Replay, and structured output, and targets the NVIDIA SM100 and Huawei Ascend 950 platforms; the published single-cluster production figures are 155 trillion tokens processed per day, a 96% input cache hit rate, 400 ms first-token latency, and a generation speed of 230 tokens/s. The report also noted that components such as KV cache management and load balancing have not yet been fully open-sourced. The next day, DeepSeek published the DeepInfer technical report on Zhihu, disclosing internal details including the hardware selection for Prefill and Decode and the KVCache targets, and providing data showing a single cluster serving 155 trillion Tokens/day at $38 per card per hour at off-peak prices. The framework is currently open-sourced, but the KV cache system, Prefill/Decode disaggregation, and load balancing required for a complete service are not fully included in this open-source project.

View story:DeepSeek open-sources inference framework DeepInfer

DeepSeek open-sources inference framework DeepInfer

On October 20, 2026, DeepSeek announced the open-sourcing of its internal production-grade inference framework, DeepInfer. According to Latent Space, the framework powers DeepSeek-V4.1-Flash, is customized based on vLLM, supports distributed inference, speculative decoding, SWA Bounded Replay, and structured output, and targets the NVIDIA SM100 and Huawei Ascend 950 platforms; the published single-cluster production figures are 155 trillion tokens processed per day, a 96% input cache hit rate, 400 ms first-token latency, and a generation speed of 230 tokens/s. The report also noted that components such as KV cache management and load balancing have not yet been fully open-sourced. The next day, DeepSeek published the DeepInfer technical report on Zhihu, disclosing internal details including the hardware selection for Prefill and Decode and the KVCache targets, and providing data showing a single cluster serving 155 trillion Tokens/day at $38 per card per hour at off-peak prices. The framework is currently open-sourced, but the KV cache system, Prefill/Decode disaggregation, and load balancing required for a complete service are not fully included in this open-source project.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

View story:English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

View story:English translation is being prepared.

English translation is being prepared.

View story:English translation is being prepared.