Default Branch

58062860af · ggml : use WARP_SIZE/2 for argmax reduction offset (#18092) · Updated 2025-12-16 19:47:01 -08:00

Branches

a7ab470832 · force patch_merger tensors to f16/f32 · Updated 2025-12-16 20:36:01 -08:00

0
1

ae303e7b87 · apparently always() is needed · Updated 2025-12-16 16:28:06 -08:00

6
4

72a41fd960 · fix missing tensor · Updated 2025-12-16 08:34:20 -08:00

7
9

e47a082fc9 · security : add collaborator guidance · Updated 2025-12-16 00:16:46 -08:00

21
1

a458664fc8 · keep file part order from model index · Updated 2025-12-14 14:35:51 -08:00

40
1

4574ab6f40 · preset: handle negated arg, reverse the meaning if needed · Updated 2025-12-14 12:44:41 -08:00

41
1

357f999381 · graph: add f_attn_temp_offset · Updated 2025-12-14 03:12:12 -08:00

45
1

292f8e231c · model-conversion : cast logits to float32 · Updated 2025-12-13 12:24:21 -08:00

57
1

2a615b27e4 · ggml : remove redundant src in ggml_cast · Updated 2025-12-09 01:16:15 -08:00

114
1

b8eb3b3501 · wip fix tests · Updated 2025-12-06 06:13:27 -08:00

160
101

31436df5ae · contrib : stale PRs · Updated 2025-12-05 12:49:15 -08:00

154
1

dad7571ff2 · tests : better input range for unary operators · Updated 2025-12-04 02:18:24 -08:00

178
1

01c9e9fd5c · llama : fix sanity checks during quantization · Updated 2025-12-03 01:10:11 -08:00

198
1

874c877bde · revise · Updated 2025-11-30 08:54:44 -08:00

245
2

c6bba89ea9 · arch : add description about LLM_TENSOR_INFOS · Updated 2025-11-27 06:03:09 -08:00

268
1

d93ff58322 · models : fix LFM2 tensors · Updated 2025-11-27 04:54:51 -08:00

268
1

05429433a1 · examples: add model-backend-compare tool to compare intermediate device tensors with CPU reference · Updated 2025-11-25 09:05:56 -08:00

290
1

72f80499ee · server : headers cleanup · Updated 2025-11-24 02:50:50 -08:00

350
5

722f9defe9 · vulkan: intel mmv fix attempt · Updated 2025-11-23 01:13:19 -08:00

312
1

c0b9903a1a · more readable · Updated 2025-11-20 08:45:37 -08:00

325
2