On the first anniversary of DeepSeek-R1's release, the new model "MODEL1" is unveiled

BlockBeats News, January 21 — On the first anniversary of DeepSeek-R1’s release, a new model “MODEL1” was exposed according to Quantum Bit. DeepSeek updated the FlashMLA code on GitHub, mentioning MODEL1 in 28 places across 114 files, appearing as a different model from V32. It is known that V32 is DeepSeek-V3.2, and MODEL1 is very likely a new architecture. The specific differences in the code are reflected in the KV cache layout, sparsity handling, and FP8 decoding, with multiple variations in memory optimization.