Skip to content

Commit dcd15a1

Browse files
TheTomclaude
andcommitted
feat: inline rotation matrices in Metal shader + C round-trip test PrismML-Eng#21
- Inlined turbo-matrices.h directly into ggml-metal.metal (256KB) to fix JIT compilation failure with #include - Added C round-trip test (test-turbo-quant.c): turbo3 cosine=0.906, turbo4 cosine=0.966 — matches Python prototype - Metal library loads successfully ("loaded in 5.9 sec") - Model runs on Metal but output quality needs debugging (Metal quantize/dequantize may have a bug vs the working C version) C round-trip PROVES the algorithm works in C. Metal shader needs debugging — likely an issue with the dequantize chunk addressing or the large constant arrays in thread-local memory. Co-Authored-By: [email protected] Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
1 parent 70a313e commit dcd15a1

2 files changed

Lines changed: 8264 additions & 1 deletion

File tree

0 commit comments

Comments
 (0)