Default Branch

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

Branches

6bfd4511f9 · Adapt to latest master · Updated 2024-09-14 18:58:39 +02:00    git

4211
3430

698c2094bb · Improve Q5_0 performance · Updated 2024-09-14 16:19:27 +02:00    git

4211
3427

349455d1f8 · Improve Q4_0 and Q8_0 performance on AVX2/Zen4 · Updated 2024-09-14 12:19:53 +02:00    git

4211
3426

cb369c22dd · Some tweaks for iq2_k and iq3_k · Updated 2024-09-13 18:50:46 +02:00    git

4211
3426

ebc88e5d9a · Fix bug and D < 128 case for Q8_0 k-cache · Updated 2024-09-13 06:17:24 +02:00    git

4211
3423

27fa27daf9 · Disallow mixing bf16 with other types for kv caches · Updated 2024-09-12 17:55:13 +02:00    git

4211
3430

95fe6923ad · Fix Zen4 · Updated 2024-09-11 18:44:34 +02:00    git

4211
3424

d063007d24 · Delete commented out stuff · Updated 2024-09-11 08:50:45 +02:00    git

4211
3423

e3919f5f80 · Fix ARM_NEON · Updated 2024-09-10 18:14:59 +02:00    git

4211
3422

65555e504c · iq2_tn: slightly better performance on AVX2 · Updated 2024-09-10 12:54:20 +02:00    git

4211
3418

8cb5e74e26 · iq2_tn: reuse iq2_bn implementation (Zen4) · Updated 2024-09-10 09:39:09 +02:00    git

4211
3418

7d8e49ef1b · Some cleanup · Updated 2024-09-10 08:08:19 +02:00    git

4211
3418

a9b15ed82e · Delete forgotten TODO · Updated 2024-09-09 19:10:11 +02:00    git

4211
3419

237a2380ee · Remove unnecessary barrier in ggml_compute_forward_mul_mat · Updated 2024-09-09 11:53:23 +02:00    git

4211
3423

b7f7eede8a · iq2_tn: slightly faster PP · Updated 2024-09-08 11:26:43 +02:00    git

4211
3414

d2225010b9 · Fused rms_norm WIP · Updated 2024-09-08 07:06:38 +02:00    git

4211
3418

8d47523e7e · Improve TG speed (when not memory bound) · Updated 2024-09-05 06:47:19 +02:00    git

4211
3414

c624232525 · Zen4 Flash Attnetion: improving bf16 · Updated 2024-09-04 16:44:29 +02:00    git

4211
3414

9d3460446d · WIP: trying to improve legacy quants · Updated 2024-09-04 06:21:38 +02:00    git

4211
3411

fffd040281 · Delete unused stuff · Updated 2024-09-03 12:12:33 +02:00    git

4211
3413