# 12 open-source alternatives to Flide

[Flide](https://ossradar.net/repo/OmniJev/Flide) (OmniJev/Flide) has 511 stars and gained +240 in the last 7 days. The extremely fast inference engine for decision model.

Below are other repos tracked by OSS Radar that share GitHub topics about what they do with Flide (platform, language and framework tags don't count), ordered by how closely their topics overlap (rarer shared topics count more), then by stars gained this week. Topic overlap means a similar problem space, not a drop-in replacement, so check each project's README. Data as of 2026-11-16T02:48:20.780Z (UTC), updated hourly. HTML page: https://ossradar.net/alternatives/OmniJev/Flide

## Alternatives

| # | Repo | Category | 7 days | Total stars | Shared topics | What it is |
| --- | --- | --- | --- | --- | --- | --- |
| 1 | [zero-to-sglang](https://ossradar.net/repo/datawhalechina/zero-to-sglang) (datawhalechina/zero-to-sglang) | LLM tooling | +399 | 2143 | CUDA, inference engine, kv cache, LLM, LLM inference | Official SGLang x Datawhale course on LLM inference: understand inference, build a mini-sglang from scratch, then read the real SGLang… |
| 2 | [PolyStrata](https://ossradar.net/repo/simplexai-labs/PolyStrata) (simplexai-labs/PolyStrata) | LLM tooling | +132 | 1085 | CUDA, Gemma, inference engine, LLM, Qwen | Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4 Flash, LFM2.5, Qwen3.6, Ornith… |
| 3 | [vLLM](https://ossradar.net/repo/vllm-project/vllm) (vllm-project/vllm) | LLM tooling | +361 | 96985 | CUDA, LLM, LLM serving, PyTorch, Qwen | A high-throughput and memory-efficient inference and serving engine for LLMs. |
| 4 | [ai-infra-book](https://ossradar.net/repo/bojieli/ai-infra-book) (bojieli/ai-infra-book) | LLM tooling | +407 | 7833 | kv cache, LLM, LLM inference, LLM serving | Open-source book that derives LLM inference and training system design from hardware limits, with calculation tools. |
| 5 | [Transformers](https://ossradar.net/repo/huggingface/transformers) (huggingface/transformers) | LLM tooling | +321 | 169031 | Gemma, LLM, PyTorch, Qwen | Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models… |
| 6 | [project-maya](https://ossradar.net/repo/mw00/project-maya) (mw00/project-maya) | LLM tooling | +199 | 2936 | CUDA, LLM, LLM inference | Run GLM-5.3 (744B), GLM-5.3-Flash (321B), DeepSeek-V4.1-Flash (748B) and MiniMax-M3.1-Flash (428B) on your own GPUs - one engine, one… |
| 7 | [Unsloth](https://ossradar.net/repo/unslothai/unsloth) (unslothai/unsloth) | LLM tooling | +323 | 79577 | Gemma, LLM, Qwen | Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more. |
| 8 | [SGLang](https://ossradar.net/repo/sgl-project/sglang) (sgl-project/sglang) | LLM tooling | +296 | 38917 | CUDA, LLM, Qwen | SGLang is a high-performance serving framework for large language models and multimodal models. |
| 9 | [OrcaReplay](https://ossradar.net/repo/Continuum-AI-Corp/OrcaReplay) (Continuum-AI-Corp/OrcaReplay) | LLM tooling | +316 | 783 | AI agents, LLM, LLM agents | OrcaReplay — Time travel for AI agents. Record, replay, fork, and debug any agent run with any model. Built by the OrcaRouter.ai team. |
| 10 | [trnrt](https://ossradar.net/repo/RunanywhereAI/trnrt) (RunanywhereAI/trnrt) | LLM tooling | +1305 | 1583 | LLM, LLM serving | The open LLM inference engine for AWS Trainium: NKI megakernels, 1M-token context, OpenAI-compatible API. By RunAnywhere. |
| 11 | [Soup](https://ossradar.net/repo/MakazhanAlpamys/Soup) (MakazhanAlpamys/Soup) | LLM tooling | +184 | 10567 | LLM, PyTorch | Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU. |
| 12 | [9router](https://ossradar.net/repo/decolua/9router) (decolua/9router) | LLM tooling | +300 | 32486 | AI agents, LLM, Qwen | Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/Gemini via 40+ providers. |

Gains marked est. are estimates for repos first seen less than a week ago. Each repo also has a Markdown page: append .md to its repo URL.

## More

- Flide repo page: https://ossradar.net/repo/OmniJev/Flide (Markdown: https://ossradar.net/repo/OmniJev/Flide.md)
- Alternatives to zero-to-sglang: https://ossradar.net/alternatives/datawhalechina/zero-to-sglang.md
- Alternatives to PolyStrata: https://ossradar.net/alternatives/simplexai-labs/PolyStrata.md
- Alternatives to vLLM: https://ossradar.net/alternatives/vllm-project/vllm.md
- Alternatives to ai-infra-book: https://ossradar.net/alternatives/bojieli/ai-infra-book.md
- Alternatives to Transformers: https://ossradar.net/alternatives/huggingface/transformers.md
- Alternatives to project-maya: https://ossradar.net/alternatives/mw00/project-maya.md
- All trending LLM tooling repos: https://ossradar.net/category/llm-tooling.md
- Alternatives to other trending repos: https://ossradar.net/alternatives
- Live leaderboard: https://ossradar.net/ (also https://ossradar.net/llms.txt and https://ossradar.net/api/v1/trending)

Free to cite with a link back to https://ossradar.net/alternatives/OmniJev/Flide.
