C++ · AGPL-3.0
shawnshekari/strixite
LLM inference engine written from scratch in HIP for AMD Strix Halo (gfx1151) and Qwen3.8-Flash-Next - ~50 tokens/s out to 492k context
★ 96
Stars
13 forks · 7 open issues
+1.0/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
26.5
Momentum / 100
see the breakdown below
34d ago
Created
last push 3d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 5.8 | +1.0/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran 0.41× the monthly pace |
| Freshness | 15 | 15.0 | last push 3d ago; decays to zero at 180 days |
| Scale | 15 | 5.8 | 96 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 26.5 | sum of the above |
Detail
| Topics | amdhipllm-inferencelocal-llmqwenrocmstrix-halo |
| Matched on | LLM & Inference (llm-inference) |
| Short window | +7 stars over 7 days = 1.0/day |
| Long window | +51 stars over 21 days = 2.4/day |
| Lifetime average | 3.03 stars/day over 32 days |
| First seen here | 2026-10-15 |
| Last read | 2d ago |