summaryrefslogtreecommitdiff
path: root/ggml/src/iqk/iqk_quantize.cpp
AgeCommit message (Expand)Author
2024-12-23MSVC fixes (#161)Kawrakow
2024-12-21IQ2_S_R4 (#156)Kawrakow
2024-12-21IQ2_XS_R4 (#155)Kawrakow
2024-12-20IQ2_XXS_R4 (#154)Kawrakow
2024-12-20IQ3_XXS_R4 (#153)Kawrakow
2024-12-18IQ4_KS_R4 (#150)Kawrakow
2024-12-18IQ5_K_R4 (#149)Kawrakow
2024-12-17Be able to repack tensors at run time (#147)Kawrakow
2024-12-17IQ2_K_R4 (#146)Kawrakow
2024-12-17IQ3_K_R4 (#145)Kawrakow
2024-12-15BF16_R16 - 16 interleaved bf16 rows (#142)Kawrakow
2024-12-14Q8_K_R8: Fastest quantized matrix multiplications (#141)Kawrakow
2024-12-12IQ4_K_R4 (#138)Kawrakow
2024-12-11Q2_K_R4 (#136)Kawrakow
2024-12-11Q3_K_R4 (#134)Kawrakow
2024-12-10Q5_K_R4 (#132)Kawrakow
2024-12-10Q6_K_R4 (#130)Kawrakow
2024-12-09Q4_K_R4 (#129)Kawrakow
2024-12-08Faster IQ4_XS_R4 on Zen4 (#128)Kawrakow
2024-12-08Rename iq4_nl_x4 to iq4_nl_r4 (#126)Kawrakow
2024-12-06iq2_bn_r4: fastest Bitnet CPU implementation on the planet (#124)Kawrakow
2024-12-04IQ4_XS_R4 (#123)Kawrakow
2024-12-03Q6_0_R4 (#122)Kawrakow
2024-12-03Q5_0_R4 (#121)Kawrakow
2024-12-03Q8_0_R4 (#120)Kawrakow
2024-12-02Q4_0_R4 (#119)Kawrakow
2024-12-02IQ4_NL_X4 (#118)Kawrakow
2024-10-25Bitnet changes (#106)Kawrakow
2024-10-16Adding IQ4_KSS: 4.0 bpw quants (#89)Kawrakow
2024-10-14Minor iq3_k tweakIwan Kawrakow
2024-10-13IQ2_KS: 2.1875 bpw non-linear quantization (#85)Kawrakow
2024-10-09New SOTA quantization: 4.25 bpw IQ4_KS (#83)Kawrakow
2024-10-04Move scale fudge factors to quantization (#81)Kawrakow
2024-09-27Adding ability to have meta data per tensor row (#61)Kawrakow
2024-09-17Fix compiler warnings (#58)Kawrakow
2024-09-09Adding IQ1_TN - 1.6875 bpw for TriLM ternary models (#44)Kawrakow
2024-08-31Fix build when iqk_mul_mat is disabled (#31)Kawrakow
2024-08-19AVX2 quantization for Q8_K (#22)Kawrakow
2024-08-09Fix MakefileIwan Kawrakow
2024-08-09Fix Zen4 implementation of iq3_k, iq4_k, iq5_kIwan Kawrakow
2024-08-09iq6_k: CUDA dequantizeIwan Kawrakow
2024-08-09iq6_k: WIP (quantize/dequantize)Iwan Kawrakow
2024-08-09iq6_k: WIP (nothing works)Iwan Kawrakow
2024-08-07Adding IQ2_TN for use with ternary models (#13)Kawrakow
2024-08-05iq3_k, iq5_k: faster quantizationIwan Kawrakow
2024-08-03iq4_k: speedup quantization by a factor of ~2Iwan Kawrakow
2024-08-01iq3_k: BasicsIwan Kawrakow
2024-08-01iq5_k: BasicsIwan Kawrakow
2024-08-01iq2_k: BasicsIwan Kawrakow
2024-07-28IQ4_K: SOTA 4-bit quantization (#6)Kawrakow
generated by cgit v1.2.3 (git 2.25.1) at 2026-01-02 21:39:41 +0000