 Eric Curtin
|
badb80cadb
Document the new max GPU layers default in help (#15771)
|
hace 4 meses |
 Johannes Gäßler
|
c466abe158
llama: -fa 1/0/-1 aliases for -fa on/off/auto (#15746)
|
hace 4 meses |
 Georgi Gerganov
|
0d161f021a
server : enable /slots by default and make it secure (#15630)
|
hace 4 meses |
|
Johannes Gäßler
|
e81b8e4b7f
llama: use FA + max. GPU layers by default (#15434)
|
hace 4 meses |
 Sigbjørn Skjæret
|
84ab83cc0b
model : jina-embeddings-v3 support (#13693)
|
hace 4 meses |
|
Georgi Gerganov
|
da54f9f1a2
presets : add qwen3-30B-a3b FIM (#15616)
|
hace 4 meses |
 Daniel Bevenius
|
fcca2182a1
common : add -m to bash completion for --model [no ci] (#15591)
|
hace 4 meses |
|
Georgi Gerganov
|
9ebebef62f
llama : remove KV cache defragmentation logic (#15473)
|
hace 4 meses |
 Diego Devesa
|
54a241f505
sched : fix possible use of wrong ids tensor when offloading moe prompt processing (#15488)
|
hace 4 meses |
 Jie Fu (傅杰)
|
ec5ab1a36c
common : fix context shift help message (#15448)
|
hace 5 meses |
 Gian-Carlo Pascutto
|
1e19f5d462
common : Add top-nsigma sampler to help globally (#15428)
|
hace 5 meses |
|
Georgi Gerganov
|
d2fcd91cf9
server : disable context shift by default (#15416)
|
hace 5 meses |
|
Georgi Gerganov
|
d32e03f449
server : add SWA checkpoints (#15293)
|
hace 5 meses |
 Jonathan Graehl
|
5cdb27e091
finetune: SGD optimizer, more CLI args (#13873)
|
hace 5 meses |
|
Sigbjørn Skjæret
|
b3e16665e1
server : enable -td and -tbd parameters (#15172)
|
hace 5 meses |
 Copilot
|
d8914fc47e
common : add --override-tensor-draft, --cpu-moe-draft and --n-cpu-moe-draft parameters (#15191)
|
hace 5 meses |
 Xuan-Son Nguyen
|
53d0a12658
server : allow specifying reasoning_format in HTTP request (#15238)
|
hace 5 meses |
|
Georgi Gerganov
|
fd1234cb46
llama : add gpt-oss (#15091)
|
hace 5 meses |
|
Diego Devesa
|
ec428b02c3
llama : add --n-cpu-moe option (#15077)
|
hace 5 meses |
 compilade
|
19f68fa5a4
imatrix : warn when GGUF imatrix is saved without .gguf suffix (#15076)
|
hace 5 meses |
|
compilade
|
d31192b4ee
imatrix : use GGUF by default (#14842)
|
hace 5 meses |
|
Diego Devesa
|
a06ed5feae
llama : add simple option to enable CPU for MoE weights (--cpu-moe) (#14992)
|
hace 5 meses |
|
Diego Devesa
|
d6818d06a6
llama : allow other bufts when overriding to CPU, add --no-repack option (#14990)
|
hace 5 meses |
 g2mt
|
94933c8c2e
server : implement universal assisted decoding (#12635)
|
hace 5 meses |
 Aman Gupta
|
8a4a856277
Add LLaDA 8b Diffusion model (#14771)
|
hace 5 meses |
 Ed Addario
|
d1aa0cc5d1
imatrix: add option to display importance score statistics for a given imatrix file (#12718)
|
hace 5 meses |
 Molly Sophia
|
adef81781a
server : allow setting `--reverse-prompt` arg (#14799)
|
hace 5 meses |
|
Georgi Gerganov
|
225e7a1438
llama : add high-throughput mode (#14363)
|
hace 6 meses |
|
Aman Gupta
|
ab14019821
Support diffusion models: Add Dream 7B (#14644)
|
hace 6 meses |
 Alawode Oluwandabira
|
17a1f0d2d4
server: Add ability to mount server at prefix (#14544)
|
hace 6 meses |
