jdelony/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-06-28 04:30:15 -05:00
Code Issues Packages Projects Releases Wiki Activity
4,666 Commits 928 Branches 1 Tag

Default Branch

main

f96eaddba8 · Revert DFlash SWA optimization (#2039) · Updated 2026-06-26 04:00:09 -05:00
 ZIP  TAR.GZ

Branches

ik/iq4_k

b29f64ea70 · iq4_k: scalar dot product · Updated 2024-07-28 05:09:28 -05:00    jdelony

4666
3355
 ZIP  TAR.GZ
ik/fuse_mul_mat_scale

473e280500 · Fusing a mat mul op followed by scale op on the CPU · Updated 2024-07-27 02:45:56 -05:00    jdelony

4666
3349
 ZIP  TAR.GZ
ik/merge_July_26_2024

573e5007cd · Remove check · Updated 2024-07-26 10:00:26 -05:00    jdelony

4666
3350
 ZIP  TAR.GZ
ik/bitnet_token_embedding_gpu_2

ccdb948329 · Offload Bitnet token embeddings to the GPU - the right way · Updated 2024-07-26 05:50:41 -05:00    jdelony

4666
3346
 ZIP  TAR.GZ
ik/bitnet_token_embedding_gpu

db6b0f6dab · Update README with the new CUDA/Meat performance · Updated 2024-07-26 02:06:22 -05:00    jdelony

4666
3346
 ZIP  TAR.GZ
ik/mul_mat_ext

86d94862ae · iqk_soft_max · Updated 2024-07-22 09:34:42 -05:00    jdelony

4666
3329
 ZIP  TAR.GZ
ik/new_iq1bn

7024ecfeb4 · iq1bn: faster AVX2 · Updated 2024-07-17 02:17:05 -05:00    jdelony

4666
3320
 ZIP  TAR.GZ