zhwu's submissions | Hacker News

1.		A collection of reproducible LLM inference engine benchmarks: SGLang vs. vLLM (github.com/michaelvll)
		1 point by zhwu 11 months ago \| past
2.		Efficient GPU Resource Management for ML Workloads Using SkyPilot, Kueue on GKE (github.com/googlecloudplatform)
		2 points by zhwu on Feb 10, 2025 \| past
3.		New Recipe: Serving Llama-2 with VLLM's OpenAI-Compatible API Server (github.com/skypilot-org)
		1 point by zhwu on Aug 22, 2023 \| past
4.		Train Your Own Vicuna on Llama-2 (github.com/skypilot-org)
		3 points by zhwu on Aug 10, 2023 \| past
5.		Guide on fine-tuning your own Vicuna on Llama-2 (twitter.com/skypilot_org)
		9 points by zhwu on Aug 3, 2023 \| past
6.		Serving LLM 24x Faster on the Cloud with VLLM and SkyPilot (skypilot.co)
		12 points by zhwu on June 29, 2023 \| past \| 1 comment
7.		Biologists are moving to the clouds with SkyPilot from UC Berkeley (twitter.com/hanq_liu)
		5 points by zhwu on May 1, 2023 \| past
8.		Vicuna releases its secrete of finding available A100s on the cloud to train it (twitter.com/lmsysorg)
		4 points by zhwu on April 13, 2023 \| past \| 2 comments