 compilade
|
d31192b4ee
imatrix : use GGUF by default (#14842)
|
vor 5 Monaten |
 Diego Devesa
|
a06ed5feae
llama : add simple option to enable CPU for MoE weights (--cpu-moe) (#14992)
|
vor 5 Monaten |
|
Diego Devesa
|
d6818d06a6
llama : allow other bufts when overriding to CPU, add --no-repack option (#14990)
|
vor 5 Monaten |
 g2mt
|
94933c8c2e
server : implement universal assisted decoding (#12635)
|
vor 5 Monaten |
 Aman Gupta
|
8a4a856277
Add LLaDA 8b Diffusion model (#14771)
|
vor 5 Monaten |
 Ed Addario
|
d1aa0cc5d1
imatrix: add option to display importance score statistics for a given imatrix file (#12718)
|
vor 5 Monaten |
 Molly Sophia
|
adef81781a
server : allow setting `--reverse-prompt` arg (#14799)
|
vor 5 Monaten |
 Georgi Gerganov
|
225e7a1438
llama : add high-throughput mode (#14363)
|
vor 6 Monaten |
|
Aman Gupta
|
ab14019821
Support diffusion models: Add Dream 7B (#14644)
|
vor 6 Monaten |
 Alawode Oluwandabira
|
17a1f0d2d4
server: Add ability to mount server at prefix (#14544)
|
vor 6 Monaten |
 matteo
|
caf5681fcb
server : support jinja extra template kwargs (Qwen3 enable_thinking feature), from command line and from client (#13196)
|
vor 6 Monaten |
 Sigbjørn Skjæret
|
88fc854b4b
llama : improve sep token handling (#14272)
|
vor 7 Monaten |
 aa956
|
d67341dc18
server : add server parameters for draft model cache type (#13782)
|
vor 7 Monaten |
|
Georgi Gerganov
|
d3e64b9f49
llama : rework embeddings logic (#14208)
|
vor 7 Monaten |
 Olivier Chafik
|
c9bbc77931
`server`: update deepseek reasoning format (pass reasoning_content as diffs) (#13933)
|
vor 7 Monaten |
 Max Krasnyansky
|
053b1539c0
threading: support for GGML_SCHED_PRIO_LOW, update thread info on Windows to avoid throttling (#12995)
|
vor 7 Monaten |
|
Georgi Gerganov
|
53f925074d
sync : vendor (#13901)
|
vor 7 Monaten |
|
Olivier Chafik
|
cdf94a1802
server: --offline mode (#13804)
|
vor 7 Monaten |
|
Olivier Chafik
|
e121edc432
`server`: add `--reasoning-budget 0` to disable thinking (incl. qwen3 w/ enable_thinking:false) (#13771)
|
vor 7 Monaten |
 Xuan-Son Nguyen
|
797990c4bc
mtmd : add ultravox audio input (#13623)
|
vor 8 Monaten |
|
Sigbjørn Skjæret
|
2aa777d86d
examples : switch retrieval to llama_encode (#13685)
|
vor 8 Monaten |
|
Georgi Gerganov
|
a4090d1174
llama : remove llama_kv_cache_view API + remove deprecated (#13653)
|
vor 8 Monaten |
|
Georgi Gerganov
|
e298d2fbd0
kv-cache : add SWA support (#13194)
|
vor 8 Monaten |
 Isaac McFadyen
|
6a2bc8bfb7
server : added --no-prefill-assistant flag (#13608)
|
vor 8 Monaten |
|
Georgi Gerganov
|
518329b2d4
parallel : add option for non-shared and larger prompts (#13598)
|
vor 8 Monaten |
 David Huang
|
7f323a589f
Add `--no-op-offload` to improve `-ot` pp perf in MoE models like llama4 400B (#13386)
|
vor 8 Monaten |
|
Xuan-Son Nguyen
|
7fef11766c
arg : add env var to control mmproj (#13416)
|
vor 8 Monaten |
|
Xuan-Son Nguyen
|
33eff40240
server : vision support via libmtmd (#12898)
|
vor 8 Monaten |
 Bartowski
|
efb8b47eda
imatrix : Add --parse-special for enabling parsing of special tokens in imatrix calculation (#13389)
|
vor 8 Monaten |
|
Georgi Gerganov
|
51fb96b1ff
context : remove logits_all flag (#13284)
|
vor 8 Monaten |
