Admin message
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
b4518
aea8ddd5
·
vulkan: fix coopmat2 validation failures (#11284)
·
Jan 20, 2025
b4516
90d987b1
·
mmap: add include for cerrno (#11296)
·
Jan 20, 2025
b4514
ec7f3ac9
·
llama : add support for Deepseek-R1-Qwen distill model (#11310)
·
Jan 20, 2025
b4513
ef6dada6
·
cont : fix whitespaces (#11305)
·
Jan 20, 2025
b4512
ae3c1db2
·
llama : re-add LLM_ARCH_PHIMOE (#11305)
·
Jan 20, 2025
b4510
b9daaffe
·
simple-chat : fix BOS being added to each message (#11278)
·
Jan 19, 2025
b4509
99487b57
·
SYCL: Introducing memory host pool (#11251)
·
Jan 19, 2025
b4508
a1649cc1
·
Adding linenoise.cpp to llama-run (#11252)
·
Jan 18, 2025
b4506
f30f0992
·
server : implement cancellable request (#11285)
·
Jan 18, 2025
b4504
6390a998
·
tts : add guide tokens support (#11186)
·
Jan 18, 2025
b4503
44e18ef9
·
vulkan: fix coopmat2 flash attention for non-contiguous inputs (#11281)
·
Jan 18, 2025
b4502
3edfa7d3
·
llama.android: add field formatChat to control whether to parse special tokens...
·
Jan 17, 2025
b4501
667d7284
·
rpc : early register backend devices (#11262)
·
Jan 17, 2025
b4500
a133566d
·
vocab : fix double-eos check (#11273)
·
Jan 17, 2025
b4499
960ec652
·
llama : fix deprecation message: vocabable -> vocab (#11269)
·
Jan 17, 2025
b4497
bd38ddea
·
vulkan: support copy from f32 to q4_0/q4_1/q5_0/q5_1/q8_0/iq4_nl (#11166)
·
Jan 16, 2025
b4493
9c8dcefe
·
CUDA: backwards pass for misc. ops, add tests (#11257)
·
Jan 16, 2025
b4491
c67cc983
·
ggml: aarch64: implement SVE kernels for q4_K_q8_K vector dot (#11227)
·
Jan 16, 2025
b4488
1d850433
·
fix: ggml: fix vulkan-shaders-gen build (#10448)
·
Jan 15, 2025
b4487
432df2d5
·
RoPE: fix back, CUDA support for back + noncont. (#11240)
·
Jan 15, 2025
1
…
27
28
29
30
31
32
33
34
35
…
178