Open Issues Need Help
View All on GitHub CUDA backend: what would have to be true for it to pay about 2 hours ago
enhancement help wanted
sqliteai/warp
2.1K
Run the full 2.78-trillion-parameter Kimi K3 model beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine.
C
UCRT64 + first real Kimi-Linear container on Windows: whole-model oracle PASS on AVX2, and five gaps no CI job can reach about 2 hours ago
bug help wanted
sqliteai/warp
2.1K
Run the full 2.78-trillion-parameter Kimi K3 model beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine.
C