feat(patterns): author Speculative Decoding entry in family 17-ai-agentic - #403
feat(patterns): author Speculative Decoding entry in family 17-ai-agentic#403mjmirza wants to merge 2 commits into
Conversation
…ntic Co-authored-by: mjmirza <34001140+mjmirza@users.noreply.github.com>
|
👋 Jules, reporting for duty! I'm here to lend a hand with this pull request. When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down. I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job! For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with New to Jules? Learn more at jules.google/docs. For security, I will only act on instructions from the user who triggered this task. |
…ntic Co-authored-by: mjmirza <34001140+mjmirza@users.noreply.github.com>
|
Review finding. this branch predates the recent family-17 work and |
Understood. Acknowledging that this pull request is closed in favor of #441 and stopping work on this task. |
…agentic (#441) * feat(patterns) author the Speculative Sampling entry in family 17-ai-agentic Rebases PR #403's entry onto current main. the branch predated a large share of the family 17 work that has since landed, so its own copies of the generated dashboards, indexes, and family README conflicted on every file except the entry itself. Pulled the content file forward unchanged and regenerated every dependent file fresh. Speculative Sampling, also known as Assisted Generation. Leviathan, Kalman, and Matias 2023 (Google Research) and Chen and colleagues 2023 (DeepMind) introduced the pattern independently. a small draft model proposes a run of tokens, the target model verifies the whole run in one forward pass, and a modified rejection sampling scheme guarantees the accepted output distribution is mathematically identical to sampling from the target model alone. Regenerates the family 17 index, BY-PROBLEM and BY-LANGUAGE, the root README and catalogue-status dashboards. Verified. check-structure.py 890/890, check-prose.py 931/931, markdownlint-cli2 0 issues, check-code.py --strict 2846 compiled with 0 failed, check-duplicates.py finds no new collision, validate-refs.py --strict resolves all 4995 citations including the entry's own arXiv, vLLM, and TensorRT-LLM sources. * fix(patterns) regenerate catalogue-status after the refs cache settled The prior commit ran gen-catalogue-status.py before validate-refs.py --strict had finished its probe pass, so references_checked locked in 5063 instead of the 5067 the cache actually held once probing completed. CI's own fresh run of the generator caught the mismatch. Re-running validate-refs.py first, then the generator last, brings README, dist/catalogue-status.json, and docs/PROGRESS.md back in sync with the real cache state.
1 participant
1. What Changes
Authors the master-level pattern entry
Speculative Decoding(patterns/17-ai-agentic/speculative-decoding.md) with all 18 mandatory dimensions, Level A/B citations (ICML 2023 primary literature, vLLM/TensorRT-LLM docs), and runnable code examples in Python, TypeScript, and Go. Updates all discovery pathways and catalogue status artefacts.2. Why This Matters
Speculative Decoding is a fundamental LLM inference acceleration technique that solves memory-bandwidth bottlenecks in autoregressive Transformer decoding by using a draft model for token proposals and a target model for parallel verification via modified rejection sampling.
3. Why Now
As of 2026, Speculative Decoding is standard across production LLM serving frameworks (vLLM, TensorRT-LLM, Apple MLX, SGLang) for low-latency agentic and interactive workloads.
4. Exact Current-Date Evidence
5. Multi-Pass Confidence Score
6. Validation
Passed all quality gates:
check-structure,check-prose,check-code --strict,check-duplicates --strict,check-claims, andmake test.PR created automatically by Jules for task 14284939946109495184 started by @mjmirza