ik_llama_opt/ggml
Yap Sok Ann 6b261d771e
cuda: fix iq3_k value table selection in MMVQ (#2364)
The per-32-block extra bits select the iq3nl_values half for each
16-element half: sub-block 4g+m, half h uses bit 8g+2m+h. The four
streams need local bits 0, 2, 4, 6, not 0, 1, 2, 3.
2026-08-27 08:40:14 +02:00
..
cmake Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
include rpc: fix crash running GLM-5.2 (glm-dsa) split over RPC (#2360) 2026-08-26 17:02:43 +02:00
src cuda: fix iq3_k value table selection in MMVQ (#2364) 2026-08-27 08:40:14 +02:00
.gitignore Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
CMakeLists.txt Chunked experts (CPU) (#2202) 2026-07-30 13:16:02 +03:00