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

b4417

9394bbd4 · llama : Add support for DeepSeek V3 (#11049) · Jan 04, 2025
b4416

f922a9c5 · [GGML][RPC] Support for models with non-512-aligned tensors over RPC. (#11047) · Jan 04, 2025
b4415

46be9422 · llama : add support for the cohere2 model architecture (#10900) · Jan 04, 2025
b4414

78c67851 · sync : ggml · Jan 04, 2025
b4411

c31fc8b9 · fix: Vulkan shader gen binary path (#11037) · Jan 04, 2025
b4409

e7da954e · metal : avoid uint (#11019) · Jan 03, 2025
b4406

0da5d860 · server : allow using LoRA adapters per-request (#10994) · Jan 02, 2025
b4404

0827b2c1 · ggml : fixes for AVXVNNI instruction set with MSVC and Clang (#11027) · Dec 31, 2024
b4403

45095a61 · server : clean up built-in template detection (#11026) · Dec 31, 2024
b4402

5896c652 · server : add OAI compat for /v1/completions (#10974) · Dec 31, 2024
b4400

6e1531ac · common, examples, ggml : fix MSYS2 GCC compiler errors and warnings when... · Dec 31, 2024
b4399

716bd6de · vulkan: optimize mul_mat for small values of N (#10991) · Dec 30, 2024
b4398

c250ecb3 · android : fix llama_batch free (#11014) · Dec 30, 2024
b4397

a813badb · vulkan: im2col and matmul optimizations for stable diffusion (#10942) · Dec 29, 2024
b4396

fdd21889 · vulkan: Use push constant offset to handle misaligned descriptors (#10987) · Dec 29, 2024
b4394

16cdce7b · server : fix token duplication when streaming with stop strings (#10997) · Dec 28, 2024
b4393

d79d8f39 · vulkan: multi-row k quants (#10846) · Dec 26, 2024
b4392

d283d02b · examples, ggml : fix GCC compiler warnings (#10983) · Dec 26, 2024
b4391

9ba399df · server : add support for "encoding_format": "base64" to the */embeddings endpoints (#10967) · Dec 24, 2024
b4390

2cd43f49 · ggml : more perfo with llamafile tinyblas on x86_64 (#10714) · Dec 24, 2024

1
…
30
31
32
33
34
35
36
37
38
…
178