Data · dataset · 2026
kleinnner/camus-10-kv-cache-quantization
Listed in Hugging Face Datasets
We attempted KV cache quantization to Q4 — and documented why it fails on the qwen2vl architecture.
Description
KV Cache Quantization Attempt: type_k/type_v on qwen2vl Architecture The Problem The KV cache consumes significant memory bandwidth during autoregressive generation. On CPU-bound systems, memory bandwidth is the primary bottleneck.
Quantizing the KV cache from FP16 to Q4 theoretically halves memory bandwidth requirements. What We Built We attempted… See the full description on the dataset page: huggingface.co/datasets/kleinnner/camus-10-kv-cache-quantization.
Links
Where it is published
- Hugging Face dataset page huggingface.co/datasets/kleinnner/camus-10-kv-cache-quantization ↗
landing page · from Hugging Face
Catalogue records · 1
- Hub API huggingface.co/api/datasets/kleinnner/camus-10-kv-cache-quantization ↗
metadata API · from Hugging Face
Topics
- From keywords
- Computer Science & AI
- Inferred from text
- Theory of computation 69%
Provenance · 1 source records, 8 field assertions
| Source | Key | Last seen | Raw |
|---|---|---|---|
| Hugging Face Datasets | kleinnner/camus-10-kv-cache-quantization | 12 d ago | JSON v1 |
| Field | Assertion | Extractor | Evidence |
|---|---|---|---|
| access_level | source · Hugging Face | connector:huggingface@1.0.0 | /gated |
| concepts[field].anzsrc:group:4613 | enrichment · Hugging Face | taxonomy-embedding@1.1.0 | title+keywords+description (69%) |
| concepts[field].local:field:computer-science-ai | mapping · Hugging Face | connector:huggingface@1.0.0 | |
| created_date | source · Hugging Face | connector:huggingface@1.0.0 | |
| description | source · Hugging Face | connector:huggingface@1.0.0 | /description |
| publication_date | source · Hugging Face | connector:huggingface@1.0.0 | |
| title | source · Hugging Face | connector:huggingface@1.0.0 | /id |
| updated_date | source · Hugging Face | connector:huggingface@1.0.0 |