nicolas
/
hybrid-llama
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
hybrid-llama/turboquant/models
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
..
templates hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
.editorconfig hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-aquila.gguf hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-baichuan.gguf hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-bert-bge.gguf hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-bert-bge.gguf.inp hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-bert-bge.gguf.out hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-command-r.gguf hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-command-r.gguf.inp hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-command-r.gguf.out hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-deepseek-coder.gguf hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-deepseek-coder.gguf.inp hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-deepseek-coder.gguf.out hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-deepseek-llm.gguf hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-deepseek-llm.gguf.inp hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-deepseek-llm.gguf.out hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-falcon.gguf hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-falcon.gguf.inp hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-falcon.gguf.out hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-gemma-4.gguf hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-gemma-4.gguf.inp hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-gemma-4.gguf.out hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-gpt-2.gguf hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-gpt-2.gguf.inp hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-gpt-2.gguf.out hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-gpt-neox.gguf hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-llama-bpe.gguf hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-llama-bpe.gguf.inp hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-llama-bpe.gguf.out hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-llama-spm.gguf hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-llama-spm.gguf.inp hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-llama-spm.gguf.out hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-mpt.gguf hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-mpt.gguf.inp hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-mpt.gguf.out hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-nomic-bert-moe.gguf hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-phi-3.gguf hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-phi-3.gguf.inp hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-phi-3.gguf.out hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-qwen2.gguf hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-qwen2.gguf.inp hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-qwen2.gguf.out hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-qwen35.gguf hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-qwen35.gguf.inp hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-qwen35.gguf.out hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-refact.gguf hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-refact.gguf.inp hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-refact.gguf.out hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-starcoder.gguf hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-starcoder.gguf.inp hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
ggml-vocab-starcoder.gguf.out hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00