michaeltrabalka-tech 632904002d vulkan: add TQ2_0 (ternary) support (llama/25850) ... * vulkan: TQ2_0 (ternary) support — dequant + dedicated mul_mat_vec + matmul via dequant_funcs First Vulkan ternary type in ggml. Correctness: OM-125m TQ2_0 vs F16 top-12 logprobs identical to 4 decimals fully offloaded (float dequant path, no Q8_K activation quant). Speed at 125m ~= F16 (overhead-bound at this scale); the bandwidth win targets larger BitNet SKUs. MMQ/int-dot path intentionally not wired yet. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * tests: enable TQ2_0 in backend-ops type lists Vulkan now implements TQ2_0 (dequant, mul_mat_vec, mul_mm, get_rows); backends without support skip via not-supported as usual. TQ1_0 stays disabled. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Michael Trabalka <michael.trabalka@sqv.ai> Co-authored-by: Claude Fable 5 <noreply@anthropic.com>		2026-08-14 22:16:06 +03:00
..
cmake	cmake : add config version support (ggml/1582)	2026-08-14 22:16:06 +03:00
include	llama: add default load-mode auto, which avoids mmap on iGPUs (llama/26081)	2026-08-14 22:16:06 +03:00
src	vulkan: add TQ2_0 (ternary) support (llama/25850)	2026-08-14 22:16:06 +03:00
.gitignore	whisper : reorganize source code + improve CMake (#2256)	2024-06-26 19:34:09 +03:00
CMakeLists.txt	cmake : add config version support (ggml/1582)	2026-08-14 22:16:06 +03:00