Unverified50% confidenceFactExact time
HSQ-A uses a lightweight scoring network to select about 15% of high-impact keys and stores the remaining values in FP8 format, thereby compressing the KV-cache from the 0.8 GB/k common in dense 70B models to 0.12 GB/k, a compression ratio of about 85%.
1
Sources
50%
Confidence
Long-term
Relevance
10/17/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedFor a 750,000-token contract document, the original KV-cache is about 90GB, which after the HSQ-A compression pipeline drops to the order of about 10GB and can fit into the remaining VRAM of an A100-40GB.75% similarUnverifiedK8V4非对称量化将Key压缩到8位、Value压缩到4位，使128K上下文的KV Cache从16GB降到约6GB74% similarUnverifiedKimi K2在FP16精度下仅模型权重就需要数百GB显存，INT4量化可将显存需求压缩至约四分之一67% similarUnverifiedFP8 KV cache is a quantization technique that compresses the Key-Value cache in the attention mechanism from FP16 or BF16 to 8 bits, which can halve the GPU memory usage of the KV cache67% similarVerifiedQuantized KV caches (such as storing KV vectors in FP8 or INT4) can compress the cache size to 1/2 or even 1/4 of the original.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1054134API
curl https://kongchang.com/api/v1/knowledge/claims/1054134MCP
get_claim(id=1054134)