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

b4389

09fe2e76 · server: allow filtering llama server response fields (#10940) · Dec 24, 2024
b4388

30caac3a · llama : the WPM vocabs use the CLS token as BOS (#10930) · Dec 24, 2024
b4387

60cfa728 · ggml : use wstring for backend search paths (#10960) · Dec 24, 2024
b4386

3327bb0f · ggml : fix arm enabled features check (#10961) · Dec 24, 2024
b4385

32d6ee63 · ggml : fix const usage in SSE path (#10962) · Dec 23, 2024
b4384

14b699ec · server : fix missing model id in /model endpoint (#10957) · Dec 23, 2024
b4383

485dc012 · server : add system_fingerprint to chat/completion (#10917) · Dec 23, 2024
b4382

86bf31cf · rpc-server : add support for the SYCL backend (#10934) · Dec 23, 2024
b4381

b92a14a8 · llama : support InfiniAI Megrez 3b (#10893) · Dec 23, 2024
b4380

6f0c9e03 · llama : support for Llama-3_1-Nemotron-51B (#10669) · Dec 23, 2024
b4379

dab76c92 · llama-run : include temperature option (#10899) · Dec 23, 2024
b4378

7024d59e · ggml : fix run-time on FreeBSD in get_executable_path() (#10948) · Dec 23, 2024
b4376

7ae33a61 · llama : add Falcon3 support (#10883) · Dec 23, 2024
b4375

ebdee947 · vulkan: build fixes for 32b (#10927) · Dec 22, 2024
b4372

e34c5af4 · ggml-cpu: replace NEON asm with intrinsics in ggml_gemv_q4_0_4x8_q8_0() (#10874) · Dec 21, 2024
b4371

eb5c3dc6 · SYCL: Migrate away from deprecated ggml_tensor->backend (#10840) · Dec 20, 2024
b4369

21ae3b9b · ggml : add test for SVE and disable when it fails (#10906) · Dec 20, 2024
b4368

0a11f8b7 · convert : fix RWKV v6 model conversion (#10913) · Dec 20, 2024
b4367

d408bb92 · clip : disable GPU support (#10896) · Dec 19, 2024
b4366

5cab3e4a · llama : minor grammar refactor (#10897) · Dec 19, 2024

1
…
31
32
33
34
35
36
37
38
39
…
178