nicolas
/
hybrid-llama
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
hybrid-llama/turboquant/docs/development
History
Marvin 1dd0700988 hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 
Base: AtomicBot-ai/atomic-llama-cpp-turboquant @ cd5609390. IQK source: ikawrakow/ik_llama.cpp @ fe215a8c (ggml/src/iqk only).

- GGML_IQK_MUL_MAT / GGML_IQK_FLASH_ATTENTION options (default OFF)

- 57 IQK repacked types, blocks, traits; IQK hooks in ggml_compute_forward_mul_mat

- ggml-cpu with IQK ON builds and links; IQK OFF build unaffected

Assisted-by: opencode (Muse Spark)
 		2026-09-05 18:09:49 -03:00
..
llama-star hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
HOWTO-add-model.md hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
debugging-tests.md hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
gemma4-assistant-tensor-inventory.md hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
parsing.md hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
pipeline-depth-2-pure-overlap.md hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
token_generation_performance_tips.md hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00