Cases Skills About

ClawIndex

OpenClaw Skills & Use Case Index

ClawIndex is an ecosystem-driven index of OpenClaw skills and real-world use cases.

Index

Meta

© 2026 ClawIndex All Rights Reserved.

Skills tagged: vLLM

Browse skills that share this tag.

serving-llms-vllm - High-throughput LLM serving framework
vLLM Inference Serving PagedAttention Continuous Batching
★ 0 · Updated 2026-09-22
High-throughput LLM serving engine supporting OpenAI compatible API, quantization, and tensor parallelism.
⚙ Deploy production LLM APIs ⚙ Run offline batch inference ⚙ Serve quantized LLM models
verl-rl-training - verl: LLM RL Training Framework
Reinforcement Learning RLHF GRPO PPO
★ 1 · Updated 2026-06-30
Flexible RL training library for large language models
⚙ train models ⚙ run rollout ⚙ compute reward
optimize-model - Optimize KServe model inference performance
Performance optimization Model inference KServe vLLM
★ 4 · Updated 2026-05-28
Analyze model code and deployment config to identify CPU/GPU optimization opportunities for KServe inference services
⚙ Read model server code ⚙ Read deployment chart ⚙ Fetch upstream guidelines
vllm-ascend-model-adapter - Adapt models for vLLM on Ascend NPU
Ascend NPU vLLM Hugging Face model adaptation
★ 0 · Updated 2026-05-11
Adapt and debug Hugging Face or local models for vLLM on Ascend NPU
⚙ collect model context ⚙ analyze model files ⚙ implement model adapter
vllm-ascend-model-adapter - vLLM Ascend NPU Model Adapter
model-adapter vLLM Ascend NPU Hugging Face
★ 0 · Updated 2026-05-11
Adapt and debug models to run vLLM on Ascend NPU
⚙ collect model context ⚙ inspect model files ⚙ analyze architecture
vllm-ascend-model-adapter - vLLM Ascend Model Adaptation
model adaptation Ascend NPU vLLM inference
★ 57 · Updated 2026-05-11
Adapt and debug models for vLLM on Ascend NPU.
⚙ analyze model architecture ⚙ implement model adapter ⚙ add processor support
vllm-ascend-model-adapter - Adapt Models for vLLM on Ascend NPU
machine learning model adaptation Hugging Face Ascend NPU
★ 2,882 · Updated 2026-05-11
Adapt and debug Hugging Face or local models to run on vLLM-Ascend with minimal changes and deterministic validation
⚙ Analyze model configuration files ⚙ Implement model adapter code ⚙ Register model architecture
unsloth-finetuning - Fine-tune LLMs with Unsloth
LLM fine-tuning 4-bit quantization LoRA
★ 602 · Updated 2026-03-26
Fine-tune LLMs with Unsloth using 4-bit quantization and LoRA
⚙ load 4-bit quantized models ⚙ configure LoRA parameters ⚙ train on datasets