 Xuan-Son Nguyen
|
7f2b2f3c77
arch: refactor LLM_TENSOR_NAMES (#18051)
|
1 месяц назад |
|
Xuan-Son Nguyen
|
7b1db3d3b7
arg: clarify auto kvu/np being set on server (#17997)
|
1 месяц назад |
 Piotr Wilkin (ilintar)
|
a5251ca11d
Optimization: Qwen3 next autoregressive pass (#17996)
|
1 месяц назад |
 Andrew Aladjev
|
fb644247de
CLI: fixed adding cli and completion into docker containers, improved docs (#18003)
|
1 месяц назад |
 2114L3
|
5f5f9b4637
server: Update README.md incorrect argument (#18073)
|
1 месяц назад |
|
Xuan-Son Nguyen
|
3d86c6c2b5
model: support GLM4V vision encoder (#18042)
|
1 месяц назад |
 Daniel Bevenius
|
9963b81f63
model-conversion : add note about verifying previous models (#18082)
|
1 месяц назад |
|
Daniel Bevenius
|
db81d5ec4b
model-conversion : use CONVERTED_EMBEDDING_MODEL for embedding_verify_logits (#18079)
|
1 месяц назад |
 Aldehir Rojas
|
c05aa69f32
common : add nemotron 3 parsing (#18077)
|
1 месяц назад |
 Francisco Herrera
|
279cef27c2
added note for old Intel hardware pre sycl (#18017)
|
1 месяц назад |
 Georgi Gerganov
|
5ba95754ee
security : add collaborator guidance (#18081)
|
1 месяц назад |
 Chris Peterson
|
2aa45ef9e3
llama: Include algorithm header needed for C++23 (#18078)
|
1 месяц назад |
|
Georgi Gerganov
|
c560316440
graph : reuse SSM graphs (#16490)
|
1 месяц назад |
 Sigbjørn Skjæret
|
d6742125c3
ci : separate webui from server (#18072)
|
1 месяц назад |
 Aleksander Grygier
|
3034836d36
webui: Improve copy to clipboard with text attachments (#17969)
|
1 месяц назад |
|
Aleksander Grygier
|
a20979d433
webui: Add setting to always show sidebar on Desktop (#17809)
|
1 месяц назад |
|
Daniel Bevenius
|
2995341730
llama : add support for NVIDIA Nemotron 3 Nano (#18058)
|
1 месяц назад |
 Darius Lukas
|
40d9c394f4
Webui: Disable attachment button and model selector button when prompt textbox is disabled. (#17925)
|
1 месяц назад |
|
Sigbjørn Skjæret
|
d6a1e18c65
convert : move rope_parameters to TextModel class (#18061)
|
1 месяц назад |
 Shouyu
|
c45f89d551
ggml-hexagon: mm for mtmd (#17894)
|
1 месяц назад |
 HelloKS
|
9d52f17ae3
model : add KORMo model (#18032)
|
1 месяц назад |
 ssweens
|
4529c660c8
kv-cache: Fix state restore fragmented cache (#17982)
|
1 месяц назад |
 Pascal
|
0f4f35e7be
Fix unreadable user markdown colors and truncate long texts in deletion dialogs (#17555)
|
1 месяц назад |
 Jeremy Demeule
|
165caaf5fb
metal: use shared buffers on eGPU (#17866)
|
1 месяц назад |
|
Xuan-Son Nguyen
|
96a181a933
mtmd: refactor audio preprocessing (#17978)
|
1 месяц назад |
|
Andrew Aladjev
|
4a4f7e6550
cli: fixed dead links to tools/main for cli and completion, fixed code owners (#17993)
|
1 месяц назад |
 Thomas Jarosch
|
e73d548659
webui: add "delete all conversations" button to import/export tab (#17444)
|
1 месяц назад |
 Johannes Gäßler
|
b1f3a6e5db
llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization (#16653)
|
1 месяц назад |
 Neo Zhang Jianyu
|
4aced7a631
[SYCL] Support gpt-oss by OPs add-id, mul_mat for mxfp4, swiglu_oai (#17826)
|
1 месяц назад |
 piDack
|
745fa0e78b
model : add glm-asr support (#17901)
|
1 месяц назад |
