DeepSeek V4.1 Gives Prefill and Decode Different Compute Paths Prompt tokens mostly traverse 20 layers; generated tokens traverse all 40. This Causal Encoder-Decoder design nearly halves long-input prefill while preserving autoregressive generation. Zhihu contributor 潜龙勿用, Changxin Ke(柯昌鑫), a graduate researcher at ICT, CAS, explains how its architecture and post-training were designed together. 1️⃣ A causal encoder, not T5 The 40-layer backbone is split into a 20-layer causal encoder and a 20-layer decoder. Both remain causal. The encoder processes the prompt and supplies the decoder’s global KV. Most prompt tokens avoid the decoder stack, while generated tokens still run through all 40 layers. That means 8B active parameters per prefill token versus 16B per decode token. 2️⃣ Most layers share global memory CSA2 uses three modes: Full creates global KV and an index; Reindex shares the KV but selects new positions; Reuse shares both. Only four layers create independent global KV, four reindex it, and 30 reuse both KV and the latest index. Each layer retains its own query and local SWA state. The first Full layer builds up to 16,384 candidates. Later layers search this pool for their Top-512. From 4K to 1M context, decode FLOPs per token rise only about 25%. 3️⃣ Serving approximations enter training Exact reconstruction of decoder SWA states would replay 2,560 prompt tokens. V4.1 replays only the final 128 encoder outputs and trains the model to tolerate the approximation. With FP4 global KV, cache falls to 890 bytes per token, persistent cache to roughly one eighth of V4-Flash, and prefill compute close to half. Bounded replay and constrained retrieval are not last-minute serving tricks. The model experiences them during post-training. 4️⃣ Post-training is an evolving Agent system Each RL task combines a problem, environment, and verifier. New trajectories can reveal shortcuts, broken environments, or verifier errors and send the task back for repair. V4.1 trains across multiple harnesses, merges checkpoints between RL runs, and finishes with on-policy distillation from more than 40 teachers. Raising reasoning effort from 25 to 100 increases output length about 2.5×, while average Pass@1 across eight benchmarks rises from 67.1% to 76.3%. ✅ The real design choice V4.1 aligns model structure, cache policy, retrieval limits, training environments, and inference around long-running Agents. The model learns under the same constraints the deployed system will actually impose. 🔗 Full analysis: #DeepSeek# #DeepSeekV41# #LLMArchitecture# #AIAgents# #LongContext# #AIInfra#

DeepSeek V4.1 Flash Is an Architecture Reset, Not Just a Cheaper Model Despite having more total and active parameters than its predecessor, V4.1 Flash cuts working KV cache to one quarter and persistent cache storage to one eighth. Zhihu contributor Exhalation explains how it does this by deleting old modules, sharing KV states, and recomputing local context. 1️⃣ DeepSeek removed its own previous ideas 🔹 MTP: external draft models such as DSpark weakened its speculative-decoding value, while the auxiliary loss no longer justified its memory cost. 🔹 Heavily Compressed Attention: its global-summary role was ambiguous and difficult to combine with FP4 storage. 🔹 Dense warmup: V4.1 trains sparse attention from scratch rather than starting with one trillion dense-attention tokens. 2️⃣ Store less, reuse more Non-SWA KV cache moves from FP8 to FP4, while the more sensitive SWA portion remains FP8. DeepSeek no longer persists SWA cache. When a conversation forks from an earlier point, the system rebuilds only a small local window. Post-training simulated this process to limit numerical drift. A modified YOCO design provides the other major saving. Upper layers reuse the same lower-layer source representation, adding only a layer-specific projection. The result is roughly half the KV storage and close to 50% less historical prefill computation in the idealized case. 3️⃣ Sparse attention reuses its search Sparse attention lowers attention cost from O(n²) to O(kn), but finding the top-k tokens can still retain an O(n²) component. V4.1 Flash either reuses an earlier layer’s top-k result or selects a smaller candidate-block pool before re-indexing. This prevents token selection from becoming the bottleneck at long context lengths. 4️⃣ Engram and mHC were streamlined Engram replaces an expensive second-order optimizer state with a Sinkhorn-style update, removes causal convolution, and extends matching from 3-grams to 4-grams. mHC reorders residual mixing across layers, reducing estimated I/O from (4n+4)d to (3n+2)d. ✅ The larger pattern DeepSeek is not merely compressing an existing model. It is willing to discard its own previous components when a cheaper system-level design emerges. V4.1 Flash is less a smaller V4 than a new answer to one question: how much intelligence can be delivered per byte of memory and unit of inference cost? 🔗 Full analysis: #DeepSeek# #DeepSeekV41# #LLMArchitecture# #AIInfra# #KVCache# #SparseAttention#

POWER OF CUDA MOAT ALERT🚨: 2 days after CUDA vLLM supported DeepSeekv4.1 Flash, AMD finally publicly released its DeepSeek v4.1 Flash image. Functionally, it works out of the box, but performance-wise, it is currently up to 14.8x worse perf per dollar than H200 and up to 42x worse perf per dollar than B200/B300 currently. The 🚀 POWER OF THE CUDA MOAT 🚀 is that NVIDIA's collaboration with its massive 6 million-developer community ecosystem means that CUDA is optimized on day 0. As AMD Anush said, "Speed is the Moat," and day 0 model support shows CUDA is the speed.

MONEY PRINTER ALERT🚨 NVIDIA vLLM B200 CAN GENERATE UP TO💰️$15 BILLION💰️OF ANNUAL PROFITS PER GIGAWATT serving the open DeepSeekv4.1 Flash model at the official interactivity & official selling prices. Using Engram DRAM offloading on NVIDIA results in a 50% increase in revenue per GigaWatt.

DeepSeek-V4-Pro-0813 just joined Token Plan, alongside Qwen3.8-Max, GLM-5.2, and more, all under one credit pool. And with Individual plans now live and Team pricing lower than before, advanced models cost less to access than ever. Go find out what fits your workload: Explore on Model Studio: Get the Token Plan: #DeepSeekV4Pro# #AlibabaCloud# #QwenCloud# #TokenPlan# #LLM# #GenerativeAI# #AIModels#