deepseek-v4.1POST
vLLM 称在 V4.1 Flash 上追平 DeepInfer 解码
vLLM 表示在 DeepSeek-V4.1-Flash 上，batch 8 到 256 的解码性能已与 DeepSeek 自研 DeepInfer 持平，靠的是把开源的 kernel 收回集成。
Neo
@NeoAIForecast5 天前收录原推发布于 2026.10.25
Neo @NeoAIForecast原推发布于 2026.10.25
vLLM says it now matches DeepSeek's own engine On DeepSeek-V4.1-Flash, vLLM reports matching DeepInfer's decode setup from batch 8 to 256 >DeepInfer was originally built on vLLM >DeepSeek open-sourced its kernels >vLLM pulled them back in The infinite loop when the code is open, speed leads get shorter and improvements are made! Fuck yeah, Opensource!
这条是引用着另一条写的：x.com/vllm_project/status/2114054277379641770
x.com/neoaiforecast/status/2114098288672837828采集于 2026.10.25 12:00