为了安全，强烈建议开启2FA双因子认证：User Settings -> Account -> Enable two-factor authentication！！！

Tags

Tags give the ability to mark specific points in history as being important

b5277

86bd60d3 · llava/mtmd : fixes to fully support dl backends (#13303) · May 04, 2025
b5276

9f2da587 · llama : build windows releases with dl backends (#13220) · May 04, 2025
b5275

93c4e239 · CUDA: fix race condition in MMQ stream-k fixup (#13299) · May 04, 2025
b5274

8afbd968 · CUDA: fix race condition in MMQ ids_dst (#13294) · May 04, 2025
b5273

8ae5ebcf · vulkan: Additional type support for unary, binary, and copy (#13266) · May 04, 2025
b5272

3e959f09 · imatrix: fix oob writes if src1 is not contiguous (#13286) · May 04, 2025
b5271

36667c8e · clip : revert the change of BOI/EOI token for GLM-edge (⚠️ breaking change) (#13259) · May 03, 2025
b5270

3bf785f3 · llama : Llama-3_1-Nemotron-Ultra-253B-v1 support (#12843) · May 03, 2025
b5269

1d36b367 · llama : move end-user examples to tools directory (#13249) · May 02, 2025
b5267

a75cb30d · context : fix reorder logic (#13267) · May 02, 2025
b5266

3f3769ba · ggml : Enable MMA for BF16 in llamafile_sgemm (#13148) · May 02, 2025
b5265

2f567611 · llama-model : support Qwen2 embedding models and pooling_mode_lasttoken (#13245) · May 02, 2025
b5261

cb06a3c3 · llama : orion rope type is neox (#13261) · May 02, 2025
b5260

626083fa · llama : plamo rope type is neox (#13260) · May 02, 2025
b5259

2af68801 · llama-chat : reset glmedge chat template (#13253) · May 02, 2025
b5258

e84773ab · mtmd-cli : fix out_of_range when input image path is empty (#13244) · May 02, 2025
b5257

fab647e8 · server : add cache reuse card link to help (#13230) · May 02, 2025
b5255

d24d5928 · ci: fix cross-compile sync issues (#12804) · May 01, 2025
b5254

8efbdadc · rpc : avoid uninitialized memory in serialize_tensor (#13210) · May 01, 2025
b5253

f057808f · ggml: Don't assert fail when tensor data changes (#13222) · May 01, 2025

Prev
1
2
3
4
5
6
7
8
…
178
Next