gputaskman (Stable) 0.4.2
What's Changed feat: show vLLM request and KV-cache gauges from /metrics as runtime-reported by @raravind007 in #67 fix(collector): normalize Windows backslashes when formatting Handy model paths by @Ujas-PersistentCoder in #70 feat(llm): report KV-cache usage and request concurrency from llama-server /metrics by @amirthn6533 in #69 Support AMD GPUs in WSL via ROCm AMD SMI by @rolandasr in #56 Add gputaskman summary for record files by @shanselman in #73 report: integer percents + shorten Intel…github.com
こちらで見つけた日
まだ来ていない日付