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

b5222

d9d398f8 · sampling : when top-k <= 0 -> noop (#13173) · Apr 29, 2025
b5221

5a639801 · llama-bench: fixed size of fields to correctly map to values (#13183) · Apr 29, 2025
b5220

cdf76586 · CUDA: fix non-cont. inputs for batched mat mul (#13155) · Apr 29, 2025
b5219

7d3af70b · llama : llm_type order by size (#13177) · Apr 29, 2025
b5218

00e3e5a1 · mtmd : add qwen2vl and qwen2.5vl (#13141) · Apr 29, 2025
b5217

e98b3692 · llama : set qwen3 model type sizes (#13175) · Apr 29, 2025
b5216

b6ce7430 · llama-graph : fix text position for mrope (#13159) · Apr 29, 2025
b5215

5f5e39e1 · model : Nomic Embed Text V2 with Mixture-of-Experts (MoE) architecture (#12466) · Apr 28, 2025
b5214

eaea3253 · clip : fix model size display (#13153) · Apr 28, 2025
b5213

43ddab6e · fix(rpc): Improve input validation and error handling (#13069) · Apr 28, 2025
b5212

1831f538 · llama-bench: add `-d` depth arg (#13096) · Apr 28, 2025
b5211

4e87962e · mtmd : fix glm-edge redundant token count (#13139) · Apr 28, 2025
b5210

fb0471d1 · context : do not clear output buffer on reserve (#13152) · Apr 28, 2025
b5209

d2b2031e · llama : (mrope) allow using normal 1D position for text token (#13138) · Apr 28, 2025
b5208

5fa9e63b · clip : refactor set input for cgraph + fix qwen2.5vl input (#13136) · Apr 28, 2025
b5207

a4c340f9 · SYCL: Add all missing unary kernels (#13074) · Apr 28, 2025
b5205

43f2b071 · common : fix noreturn compile warning (#13151) · Apr 28, 2025
b5204

e5d6c255 · llama-chat : fix typo GML --> GLM (#13143) · Apr 28, 2025
b5202

69699be4 · CUDA: fix q_nope_absorbed prec for DS 2 Lite f16 (#13137) · Apr 28, 2025
b5201

85f36e5e · arg : fix unused variable (#13142) · Apr 28, 2025

Previous
1
2
3
4
5
6
7
8
9
10
…
178
Next