# apple-aiml-research/ml-rsi-inference-bench

> A benchmark for evaluating coding agents that optimize and repair the LLM inference stack in real engines like vLLM and SGLang on real GPUs. Agents work on the live engine and are graded by running what they built.

- Magnitude: 1.3 out of 10 — Cooling
- Stars: 99 total · +0 stars measured 2026-10-20, 00:23–01:55 UTC, ≈ 7 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · Created: 2026-10-16 · Last push: 2026-10-16
- GitHub: https://github.com/apple-aiml-research/ml-rsi-inference-bench · Page: https://gitnova.dev/en/r/apple-aiml-research/ml-rsi-inference-bench

## Useful for

- Run your agent on the benchmark tasks via Pier and get two scores
- Compare models and agents on inference optimization quality on GPUs
- Test how an agent handles regressions in vLLM or SGLang

## Why it’s here

- Star-counter measurements on 2026-10-20 (UTC), 00:23–01:55: 99 → 99 stars (+0). This is the change over that interval.
- Estimated end-of-day forecast: about +7 stars, using observed gains and the previous day.
- The repository is 4 days old and already has 99 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #197.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 3
- Issues and pull requests: 0
- Watchers: 2
- Average over the last week: 21 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 0

## Stars per day, last 5 days (oldest → newest, today is partial)

2026-10-16 … 2026-10-20: 18, 55, 18, 8, 0

## Spotted in now

- Top new repositories this week: #197

## More in this category

1. **mistralai/timestral** — 5.7 · Early signal · Language models · Python · +10 stars measured 2026-10-20, 00:22–01:47 UTC, ≈ 161 by evening
   A family of pretrained foundation models for multivariate probabilistic time series forecasting with covariate support. Enables zero-shot forecasting on CPU or GPU without training.
   Full card: https://gitnova.dev/en/r/mistralai/timestral.md
2. **solidsf-inc/solidcv** — 5.5 · Early signal · Language models · Rust · +4 stars measured 2026-10-20, 00:23–01:47 UTC, ≈ 113 by evening
   A pure-Rust OpenCV replacement with zero FFI: classical 2D/3D vision, stereo reconstruction, and mechanistic interpretability for LLMs/VLMs with hardware kernels for Apple Silicon and NVIDIA.
   Full card: https://gitnova.dev/en/r/solidsf-inc/solidcv.md
3. **headroomlabs-ai/headroom** — 4.9 · Breakout · Language models · Python · +35 stars measured 2026-10-20, 00:23–01:48 UTC, ≈ 363 by evening
   A local library, proxy and MCP server that compress tool outputs, logs, files and RAG chunks before they reach the LLM, cutting token usage without changing answers.
   Full card: https://gitnova.dev/en/r/headroomlabs-ai/headroom.md
4. **nace-ai/kapitsa** — 4.4 · Early signal · Language models · C++ · +2 stars measured 2026-10-20, 00:22–01:48 UTC, ≈ 33 by evening
   Apple Silicon optimized inference engine for Qwen and Nemotron models with OpenAI- and Anthropic-compatible APIs. Runs local LLMs on Mac via CLI and a web chat.
   Full card: https://gitnova.dev/en/r/nace-ai/kapitsa.md
5. **mudler/LocalAI** — 4.3 · Breakout · Language models · Go · +6 stars measured 2026-10-20, 00:24–01:48 UTC, ≈ 103 by evening
   LocalAI is an open-source AI engine that runs LLMs, vision, voice, image and video models on any hardware, including CPU-only, behind an OpenAI-compatible API.
   Full card: https://gitnova.dev/en/r/mudler/LocalAI.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-20 01:58 UTC, updated every 30 minutes.