All skills
emerging-techniques-speculative-decoding
Speeds up model inference with speculative decoding, Medusa heads and lookahead decoding.
- Part of davila7/claude-code-templates
- Machine Learning · Model serving
More Model serving skills
See all- agent-platform-deploy10.3kDeploys models from Model Garden to endpoints and cleans up deployments when done.
- agent-platform-inference9.6kRuns prompts and chat completions against Gemini and third-party models on Google Cloud.
- serving-llms-vllm66Serves large language models at high throughput with an OpenAI-compatible API and quantization.
- omh-inference-serving31Helps choose a serving engine and set up self-hosted LLM serving on GPUs.
Also in this pack
- prompt-engineer1.5kDesigns effective prompts for LLM applications, covering structure, context, output format and evaluation.
- marketing-strategy-pmm1.4kHelps with product positioning, go-to-market plans, launch playbooks, and competitive battlecards.
- google-analytics1.2kAnalyzes Google Analytics data to explain traffic, conversions and user behavior, then suggests improvements.
- jira1.2kCreates, views and updates Jira issues and checks sprint status from the conversation.