🚀 MegaETH Co-Founder Discusses Recent RPC Outage and Future Plans
#MegaETH #RPCoutage #infrastructure #memorymanagement #performanceoptimization #postmortem #communityengagement #edgecases
According to Foresight News, MegaETH co-founder Lei Yang recently addressed an RPC outage that revealed an intriguing edge case. The incident occurred when debugging RPC method calls led to the server allocating excessive memory for an overly long string, ultimately resulting in memory exhaustion. In response, the MegaETH team has decided to build their own RPC stack to implement various optimizations aimed at enhancing performance. While this approach has yielded positive performance results, it requires the team to manage infrastructure maintenance independently.
Yang anticipates more outages in the future and plans to release additional post-mortem reports, hoping these will spark engaging discussions. He encourages the community to share more edge cases for testing now, rather than encountering issues months later.#MegaETH #RPCoutage #infrastructure #memorymanagement #performanceoptimization #postmortem #communityengagement #edgecases
🚀 DeepSeek Unveils New Model 'MODEL1' on Anniversary of DeepSeek-R1
#DeepSeek #MODEL1 #DeepSeekR1 #FlashMLA #GitHub #V32 #DeepSeekV32 #KVCacheLayout #SparsityHandling #FP8Decoding #MemoryManagement
On January 21, DeepSeek marked the first anniversary of DeepSeek-R1 by revealing details about its new model, 'MODEL1.' According to BlockBeats, the company updated its FlashMLA code on GitHub, highlighting 28 mentions of MODEL1 across 114 files. This model appears alongside V32, indicating it is distinct from DeepSeek-V3.2. The differences in the code are evident in areas such as KV cache layout, sparsity handling, and FP8 decoding, with several optimizations in memory management.#DeepSeek #MODEL1 #DeepSeekR1 #FlashMLA #GitHub #V32 #DeepSeekV32 #KVCacheLayout #SparsityHandling #FP8Decoding #MemoryManagement