Reasoning: From Reflection to Solution
Paper • 2511.11712 • Published • 2
Zixi "Oz" Li PRO
OzTianlu
AI & ML interests
My research focuses on deep reasoning with small language models, Transformer architecture innovation, and knowledge distillation for efficient alignment and transfer.
Recent Activity
liked a model 4 days ago
google/gemma-4-26B-A4B-it reacted to theirpost with 🤗 10 days ago
https://github.com/lizixi-0x2F/March
I just released March, an open-source high-performance KV cache sharing library for LLM inference that uses Trie-based prefix deduplication.
When you run LLM services, you often see thousands of requests sharing the same system prompt and conversation history. But traditional KV cache systems store each sequence separately — duplicating the exact same data over and over again. Pure waste.
March uses a Trie structure to automatically detect and reuse identical token prefixes. Instead of storing [system_prompt + history] 1000 times, it's stored once. Everyone shares it.
- 80-97% memory reduction in prefix-heavy workloads (tested on SmolLM2-135M with 500 multi-turn conversations)
- Zero-copy queries — returns direct pointers into the memory pool, no expensive memcpy on the hot path
- Predictable memory usage — fixed-size page pool with O(L) complexity
- Trade-off: slightly slower than dict O(1) lookup, but the memory savings are worth it in production posted an update 10 days ago
https://github.com/lizixi-0x2F/March
I just released March, an open-source high-performance KV cache sharing library for LLM inference that uses Trie-based prefix deduplication.
When you run LLM services, you often see thousands of requests sharing the same system prompt and conversation history. But traditional KV cache systems store each sequence separately — duplicating the exact same data over and over again. Pure waste.
March uses a Trie structure to automatically detect and reuse identical token prefixes. Instead of storing [system_prompt + history] 1000 times, it's stored once. Everyone shares it.
- 80-97% memory reduction in prefix-heavy workloads (tested on SmolLM2-135M with 500 multi-turn conversations)
- Zero-copy queries — returns direct pointers into the memory pool, no expensive memcpy on the hot path
- Predictable memory usage — fixed-size page pool with O(L) complexity
- Trade-off: slightly slower than dict O(1) lookup, but the memory savings are worth it in productionOrganizations
authored a
paper 3 months ago