feat: port TQ3_0 KV cache from llama-turboquant#2

Open

carlosfundora wants to merge 6 commits intoPrismML-Eng:prismfrom

carlosfundora:feature/tq3_0-kv-cache

Commits on Mar 2, 2026

ggml: add Q1_0 and Q1_0_g128 1-bit quantization support (CPU, Metal, CUDA)
khosravipasha
committed

Commits on Mar 13, 2026

[cuda] fix mmq/mma path
khosravipasha
committed

Commits on Mar 19, 2026

Merge pull request #1 from PrismML-Eng/mmq
khosravipasha
authored

Commits on Mar 24, 2026

simplify dequantize_row_q1_0_g128
khosravipasha
committed

Commits on Mar 25, 2026

add slim release workflow for prism
khosravipasha
committed

Commits on Apr 1, 2026

feat: port TQ3_0 KV cache quantization from llama-turboquant
sentseven
committed