RadixArk
@radixark
Miles brings Day-0 RL support to DeepSeek-V4.1-Flash.
Miles keeps the trainer close to what @sgl_project samples. Parallelism and shared state let the new architecture scale intact across GPUs. Quantization-aware training mirrors SGLang's FP4/FP8 rounding, while routing replay
Miles keeps the trainer close to what @sgl_project samples. Parallelism and shared state let the new architecture scale intact across GPUs. Quantization-aware training mirrors SGLang's FP4/FP8 rounding, while routing replay
SGLang@sgl_project · Sep 10DeepSeek V4.1 Flash weights are out! We are shipping day-0 inference and RL support in SGLang and Miles.
V4.1 extends the V4 stack with compressed KV shared across layers, a two-stage sparse indexer, and a 196B Engram lookup memory.
It is natively multimodal with 552B backbone
V4.1 extends the V4 stack with compressed KV shared across layers, a two-stage sparse indexer, and a 196B Engram lookup memory.
It is natively multimodal with 552B backbone
0:06 2 46