Default Branch

b2cb4512c5 · Create parameters overview (#1269) · Updated 2026-02-20 07:20:56 +01:00

Branches

882f52032a · Be able to re-quantize MS BitNet I2_S models · Updated 2025-01-10 16:43:44 +01:00    git

4211
3527

8174b7f538 · q8_k16: use integer arithmetic to sum row values · Updated 2025-01-10 13:08:41 +01:00    git

4211
3527

9f8cd4049a · q8_k16: use integer arithmetic to sum row values · Updated 2025-01-10 13:01:01 +01:00    git

4211
3530

8bc80e08d0 · Adapt to iq4_nl_x4 -> iq4_nl_r4 change · Updated 2025-01-09 10:58:25 +01:00    git

4211
3528

1f785d2a3a · iq4_0_r4: Use AVX2 version for matrix x vector · Updated 2024-12-23 17:30:47 +01:00    git

4211
3525

c794281b8e · iq3_s_r4: rearranged quants - NEON · Updated 2024-12-23 13:51:32 +01:00    git

4211
3530

b31c3e9103 · iq3_s_r4: NEON · Updated 2024-12-22 20:25:47 +01:00    git

4211
3527

4e36826d51 · One more · Updated 2024-12-22 18:14:51 +01:00    git

4211
3524

4de66b9248 · qx_0_r4(AVX2): convert scales with SIMD instrinsics · Updated 2024-12-22 11:26:17 +01:00    git

4211
3523

7f7bc3a37f · r4_nrcy_16: iq3_k_r4, iq4_k_r4, iq4_ks_r4, iq5_k_r4 · Updated 2024-12-22 09:25:01 +01:00    git

4211
3526

fe8eda7b47 · iq2_s_r4: NEON · Updated 2024-12-21 11:13:58 +01:00    git

4211
3522

6dddd0832a · iq2_xs_r4: slightly better NEON · Updated 2024-12-21 08:15:35 +01:00    git

4211
3523

c3e9a0e26f · iq2_xxs_r4: NEON · Updated 2024-12-20 11:46:37 +01:00    git

4211
3519

3681093127 · iq3_xxs_r4: NEON · Updated 2024-12-20 09:04:07 +01:00    git

4211
3519

1875b1d8e6 · iq3_xxs_r4: NEON · Updated 2024-12-19 17:47:39 +01:00    git

4211
3525

baa9ed4a5e · Minor · Updated 2024-12-18 19:14:40 +01:00    git

4211
3521

6c935be1c0 · iq5_k_r4: NEON · Updated 2024-12-18 13:21:30 +01:00    git

4211
3520

c367b15c5f · Minor · Updated 2024-12-17 18:53:44 +01:00    git

4211
3514

e716ae7778 · Repack: make sure number of rows is a multiple of the packing · Updated 2024-12-17 14:14:36 +01:00    git

4211
3514

a75a790e8f · iq2_k_r4: better matrix x vector multiplication on NEON · Updated 2024-12-17 10:06:02 +01:00    git

4211
3513