Repository · GitHub

huawei-csl/KVarN

KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Calibration-free, one flag.

View on GitHubReport an issue

Owner	huawei-csl
License (as declared)	Apache-2.0
Stars	510
Forks	37
Main language	Python
Created	29 May 2026
Last updated at source	22 June 2026

pythonagentic-aikv-cachellmllm-inferencelong-contextquantizationvllm

Embed this entry

<iframe src="https://silytics.si/embed/item/c76b4f2b-0b13-47cf-973a-a4e4ee2cf3be" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

Stars, last 3 days

510 now. Counts as reported by the source, snapshotted daily by Silytics.

More from huawei-csl

SINQRepository

Silytics shows public metadata from GitHub and links to the original. Information may be incomplete or out of date. Last refreshed 18 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.