Default Branch

17313a4226 · Fix cuda memory error for Qwen3 non-quantized (#2987) · Updated 2025-06-07 14:02:58 +00:00

Branches

a394dfe4c1 · Update imageproc requirement from 0.24.0 to 0.25.0 · Updated 2024-05-21 19:49:19 +00:00    huggingface

343
1

567247fdcf · Update metal requirement from 0.27.0 to 0.28.0 · Updated 2024-05-21 19:45:53 +00:00    huggingface

344
1

f7980abbcd · Improve the sampling methods. · Updated 2024-05-04 08:53:30 +00:00    huggingface

358
1

6d6d87f8b3 · Use BF16 for llama v3 by default. · Updated 2024-04-19 12:22:01 +00:00    huggingface

396
1

3754b834f4 · More prep work for phi. · Updated 2024-04-17 08:23:15 +00:00    huggingface

403
3

6e92129f54 · Add missing bfloat unary strided kernels · Updated 2024-04-11 14:20:45 +00:00    huggingface

424
3

33c9b66554 · Add the new gemma models. (#2023) · Updated 2024-04-06 19:25:38 +00:00    huggingface

431
0
Included

09fafcfa99 · Copy multi metal [do not merge] · Updated 2024-04-06 08:11:16 +00:00    huggingface

434
1

8c0db87992 · Avoid using the attn mask when not necessary. · Updated 2024-03-24 17:55:56 +00:00    huggingface

497
0
Included

5ac3302fac · Prebuild all our kernels. · Updated 2024-03-18 15:39:38 +00:00    huggingface

606
1

53f951f6e2 · Merge remote-tracking branch 'origin/main' into cuda-conv-tr1d · Updated 2024-03-17 20:17:56 +00:00    huggingface

533
6

101a4c8389 · Moondream first bits. · Updated 2024-03-17 16:49:56 +00:00    huggingface

535
1

9dc53ec8ad · Last push. · Updated 2024-03-05 22:18:30 +00:00    huggingface

556
5

3f3730b657 · Preliminary implementation for the vocos model. · Updated 2024-02-14 21:16:09 +00:00    huggingface

609
1

e2bf0adc2a · [WIP] Bf16 support. · Updated 2024-02-13 21:44:11 +00:00    huggingface

615
1

8babfe0411 · Fixed all bugs. Improved code quality. Added tests. · Updated 2024-01-30 13:40:46 +00:00    huggingface

662
6

933716b374 · Where cond get_strided_index conditionally based on function constants · Updated 2024-01-23 19:40:29 +00:00    huggingface

662
1

ceaf7f1e2d · More concise macros · Updated 2024-01-22 20:20:31 +00:00    huggingface

662
13

67d93b4f42 · More happy tests. · Updated 2024-01-15 17:46:18 +00:00    huggingface

685
11

5637f86040 · Update yew requirement from 0.20.0 to 0.21.0 · Updated 2024-01-15 12:25:36 +00:00    huggingface

685
1