DeepSeek-V4 on Day 0: From Fast Inference to Verified RL with SGLang and Miles
DeepSeek-V4 is now supported for both inference and reinforcement learning (RL) training from Day 0. SGLang and Miles provide the first open-source stack designed for DeepSeek-V4’s hybrid sparse-attention architecture and manifold-constrained hyper-connections, utilizing FP4 expert weights.
lmsys.org
17 min
16h ago
DeepSeek-V4 on Day 0: From Fast Inference to Verified RL with SGLang and Miles
DeepSeek-V4 is now supported for both inference and reinforcement learning (RL) training from Day 0. SGLang and Miles provide the first open-source stack designed for DeepSeek-V4’s hybrid sparse-attention architecture and manifold-constrained hyper-connections, utilizing FP4 expert weights.
lmsys.org
17 min
16h ago
DeepSeek-V4 on Day 0: From Fast Inference to Verified RL with SGLang and Miles
DeepSeek-V4 is now supported for both inference and reinforcement learning (RL) training from Day 0. SGLang and Miles provide the first open-source stack designed for DeepSeek-V4’s hybrid sparse-attention architecture and manifold-constrained hyper-connections, utilizing FP4 expert weights.
lmsys.org
17 min
16h ago
No more articles to load