Live data from Hacker News

Show HN: KVBoost – chunk-level KV cache reuse for HuggingFace, 5–48x faster TTFT

pythongiant.github.io

21–23 of 23 posts

Re: Show HN: KVBoost – chunk-level KV cache reuse for HuggingFace, 5–48x faster TTFT

#23

Drop in replacement for what exactly? Can I use it with llama.cpp and Vulkan? Or vLLM and ROCm?

KVBoost is a drop-in replacement for AutoModelForCausalLM. Same API surface (KVBoost.from_pretrained(...), engine.generate(...)), but with cross-request KV reuse, FlashAttention-2, AWQ layer streaming, and speculative decoding bolted on.
Post reply on HN