peonist-ai/halogen-flash-server

halogen-flash-server

✅ Recently maintained

Local inference that behaves like a frontier API: Qwen3.8-Flash-Next on AMD Strix Halo plus small NPU models, over the OpenAI and Anthropic APIs on one port.

1,196Stars
80Forks
+777-day stars

Shell · License unverified · Last push 2026-10-31

Official repository & installation ↗
amdgfx1151gpu-inferencehipinference-enginellmllm-servinglocal-llmlong-contextmixture-of-experts

GitValue · Value evidence

Unscored · Evidence coverage 0%

Provisional rubric; documentation and runtime testing are separate. Missing evidence does not imply low value.

Star history

2026-08-242026-11-02
View historical data
DateStars
2026-10-04833
2026-10-05850
2026-10-06861
2026-10-07874
2026-10-08888
2026-10-09910
2026-10-10927
2026-10-11935
2026-10-12947
2026-10-13959
2026-10-14977
2026-10-15998
2026-10-161,007
2026-10-171,012
2026-10-181,020
2026-10-191,035
2026-10-201,044
2026-10-211,065
2026-10-221,072
2026-10-231,080
2026-10-241,087
2026-10-251,102
2026-10-261,113
2026-10-271,129
2026-10-281,133
2026-10-291,139
2026-10-301,145
2026-10-311,163
2026-11-011,178
2026-11-021,196

Get the project

git clone https://github.com/peonist-ai/halogen-flash-server.git

Cloning downloads the source. For dependencies and installation, follow the project README.

Related projects & alternative candidates

Related domains do not imply feature parity. Review official documentation and licenses.

vllm

High-throughput, memory-efficient LLM inference and serving engine that lets developers deploy models faster without building serving infrastructure.

★ 96,180litellm

Call 100+ LLM APIs using the OpenAI input/output format.

★ 62,604nanobot

Lightweight swarm intelligence experimental platform for micro-agents.

★ 49,776