Default Branch

f114f91f9e · tests : initialize the L2_NORM batch array (#28553) · Updated 2026-09-07 19:54:13 +02:00

Branches

3b54531ead · ci : disable mmap · Updated 2025-12-28 08:26:51 +01:00    Superminaren

3294
1

5f14aa8e43 · gguf-py : do not align the data start offset · Updated 2025-12-22 15:49:54 +01:00    Superminaren

3349
1

6b1394ed74 · prof: fix tensor dims formatter · Updated 2025-12-18 02:11:21 +01:00    Superminaren

3386
3

e47a082fc9 · security : add collaborator guidance · Updated 2025-12-16 09:16:46 +01:00    Superminaren

3427
1

292f8e231c · model-conversion : cast logits to float32 · Updated 2025-12-13 21:24:21 +01:00    Superminaren

3463
1

2a615b27e4 · ggml : remove redundant src in ggml_cast · Updated 2025-12-09 10:16:15 +01:00    Superminaren

3520
1

31436df5ae · contrib : stale PRs · Updated 2025-12-05 21:49:15 +01:00    Superminaren

3560
1

dad7571ff2 · tests : better input range for unary operators · Updated 2025-12-04 11:18:24 +01:00    Superminaren

3584
1

01c9e9fd5c · llama : fix sanity checks during quantization · Updated 2025-12-03 10:10:11 +01:00    Superminaren

3604
1

c6bba89ea9 · arch : add description about LLM_TENSOR_INFOS · Updated 2025-11-27 15:03:09 +01:00    Superminaren

3674
1

d93ff58322 · models : fix LFM2 tensors · Updated 2025-11-27 13:54:51 +01:00    Superminaren

3674
1

05429433a1 · examples: add model-backend-compare tool to compare intermediate device tensors with CPU reference · Updated 2025-11-25 18:05:56 +01:00    Superminaren

3696
1

72f80499ee · server : headers cleanup · Updated 2025-11-24 11:50:50 +01:00    Superminaren

3756
5

722f9defe9 · vulkan: intel mmv fix attempt · Updated 2025-11-23 10:13:19 +01:00    Superminaren

3718
1

6cdda87baf · ci : disable op offload in some tests · Updated 2025-11-20 16:16:50 +01:00    Superminaren

3763
3

dba1cbceb3 · tune for RDNA3 · Updated 2025-11-16 20:21:22 +01:00    Superminaren

3771
4

e6dbc81569 · metal : cap threadgroups size of set_rows · Updated 2025-11-10 15:17:09 +01:00    Superminaren

3840
1

3ad533689c · ggml : remove KQ mask padding · Updated 2025-11-10 13:35:25 +01:00    Superminaren

3842
1

2ef41855cf · convert : for FP8, use scale type to decide auto type · Updated 2025-11-07 04:55:53 +01:00    Superminaren

3880
16

e996f3aef8 · convert : fix no-lazy dtypes from direct safetensors · Updated 2025-11-07 04:33:09 +01:00    Superminaren

3880
3