zero-to-sglang alternatives
datawhalechina/zero-to-sglang (2.1k stars, +399 this week): Official SGLang x Datawhale course on LLM inference: understand inference, build a mini-sglang from scratch, then read the real SGLang…
Below are 7 other LLM tooling repos tracked by OSS Radar that share at least two GitHub topics about what they do with zero-to-sglang (platform, language and framework tags don't count), ordered by how closely their topics overlap (rarer shared topics count more), then by stars gained in the last 7 days. Topic overlap means a similar problem space, not a drop-in replacement, so check each project's README.
1. FlideOmniJev/Flide
+240/wkThe extremely fast inference engine for decision model.
511 stars · Python · shared topics: CUDA, inference engine, kv cache, LLM, LLM inference · Flide alternatives
2. ai-infra-bookbojieli/ai-infra-book
+407/wkOpen-source book that derives LLM inference and training system design from hardware limits, with calculation tools.
7.8k stars · Python · shared topics: kv cache, LLM, LLM inference · ai-infra-book alternatives
3. PolyStratasimplexai-labs/PolyStrata
+132/wkRun 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…
1.1k stars · C++ · shared topics: CUDA, inference engine, LLM · PolyStrata alternatives
4. project-mayamw00/project-maya
+199/wkRun 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…
2.9k stars · C++ · shared topics: CUDA, LLM, LLM inference · project-maya alternatives
5. ai-engineering-from-scratchrohitg00/ai-engineering-from-scratch
+917/wkLearn AI Engineering! Learn it. Build it. Ship it for others.
79k stars · Python · shared topics: LLM, tutorial · ai-engineering-from-scratch alternatives
6. vLLMvllm-project/vllm
+361/wkA high-throughput and memory-efficient inference and serving engine for LLMs.
97k stars · Python · shared topics: CUDA, LLM · vLLM alternatives
7. SGLangsgl-project/sglang
+296/wkSGLang is a high-performance serving framework for large language models and multimodal models.
39k stars · Python · shared topics: CUDA, LLM · SGLang alternatives
More: all trending LLM tooling repos · trending LLM repos · compare zero-to-sglang with the top 2 · alternatives to other trending repos