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

b3396

9104bc20 · common : add --no-cont-batching arg (#6358) · Jul 15, 2024
b3394

16bdfa42 · [SYCL] add concat through dim 1/2 (#8483) · Jul 15, 2024
b3393

3dfda059 · llama : de-duplicate deepseek2 norm · Jul 15, 2024
b3392

bda62d79 · Vulkan MMQ Fix (#8479) · Jul 15, 2024
b3389

73cf442e · llama : fix Gemma-2 Query scaling factors (#8473) · Jul 14, 2024
b3387

fa79495b · llama : fix pre-tokenization of non-special added tokens (#8228) · Jul 13, 2024
b3386

17eb6aa8 · vulkan : cmake integration (#8119) · Jul 13, 2024
b3385

c917b67f · metal : template-ify some of the kernels (#8447) · Jul 13, 2024
b3384

4e24cffd · server : handle content array in chat API (#8449) · Jul 12, 2024
b3383

6af51c0d · main : print error on empty input (#8456) · Jul 12, 2024
b3382

f5322624 · llama : suppress unary minus operator warning (#8448) · Jul 12, 2024
b3381

c3ebcfa1 · server : ensure batches are either all embed or all completion (#8420) · Jul 12, 2024
b3378

71c1121d · examples : sprintf -> snprintf (#8434) · Jul 12, 2024
b3376

b549a1bb · [SYCL] fix the mul_mat_id ut issues (#8427) · Jul 12, 2024
b3375

36864569 · ggml : add NVPL BLAS support (#8329) (#8425) · Jul 11, 2024
b3374

b078c619 · cuda : suppress 'noreturn' warn in no_device_code (#8414) · Jul 11, 2024
b3373

808aba39 · CUDA: optimize and refactor MMQ (#8416) · Jul 11, 2024
b3371

9a55ffe6 · tokenize : add --no-parse-special option (#8423) · Jul 11, 2024
b3370

7a221b67 · llama : use F32 precision in Qwen2 attention and no FA (#8412) · Jul 11, 2024
b3369

278d0e18 · Initialize default slot sampling parameters from the global context. (#8418) · Jul 10, 2024

1
…
65
66
67
68
69
70
71
72
73
…
178