 ddh0
|
13f1e4a9ca
llama : add adaptive-p sampler (#17927)
|
2 weeks ago |
 Adrien Gallouët
|
516a4ca9b5
refactor : remove libcurl, use OpenSSL when available (#18828)
|
2 weeks ago |
 Radoslav Gerganov
|
bcf7546160
server : add arg for disabling prompt caching (#18776)
|
2 weeks ago |
 Daniel Bevenius
|
4150da9a95
examples : add --kv-unified to batched example (#18774)
|
2 weeks ago |
 Xuan-Son Nguyen
|
23f82f2420
preset: allow named remote preset (#18728)
|
2 weeks ago |
|
Adrien Gallouët
|
ea23c15990
common : add --license to display embedded licenses (#18696)
|
2 weeks ago |
|
Xuan-Son Nguyen
|
8ece3836b4
common: support remote preset (#18520)
|
3 weeks ago |
 Johannes Gäßler
|
64848deb18
llama-fit-params: free memory target per device (#18679)
|
3 weeks ago |
 Julius Tischbein
|
2038101bd9
llama : add `use_direct_io` flag for model loading (#18166)
|
3 weeks ago |
|
Adrien Gallouët
|
56d2fed2b3
tools : remove llama-run (#18661)
|
3 weeks ago |
|
Daniel Bevenius
|
ffba4f29e6
examples : add debug utility/example (#18464)
|
3 weeks ago |
|
Xuan-Son Nguyen
|
07fbe19f1f
arg: use CSV escape style for multiple-value args (#18643)
|
3 weeks ago |
|
Daniel Bevenius
|
d3dce4e0a5
sampling : add support for backend sampling (#17004)
|
3 weeks ago |
 o7si
|
60f17f56da
rpc: fix segfault on invalid endpoint format (#18387)
|
1 month ago |
|
Johannes Gäßler
|
026d2ad472
llama: fix magic number of 999 for GPU layers (#18266)
|
1 month ago |
|
Xuan-Son Nguyen
|
f5acfb2ffa
server: (router) add stop-timeout option (#18350)
|
1 month ago |
 ddh0
|
10355dc7d0
common: add `LLAMA_ARG_OVERRIDE_TENSOR` env var for `-ot` arg (#18267)
|
1 month ago |
|
Xuan-Son Nguyen
|
ddcb75dd8a
server: add auto-sleep after N seconds of idle (#18228)
|
1 month ago |
|
Xuan-Son Nguyen
|
9e39a1e6a9
server: support load model on startup, support preset-only options (#18206)
|
1 month ago |
 Pascal
|
14931a826e
arg: fix order to use short form before long form (#18196)
|
1 month ago |
|
Xuan-Son Nguyen
|
98c1c7a7bf
presets: refactor, allow cascade presets from different sources, add global section (#18169)
|
1 month ago |
|
Xuan-Son Nguyen
|
8ea958d4d9
model : add ASR support for LFM2-Audio-1.5B (conformer) (#18106)
|
1 month ago |
|
Xuan-Son Nguyen
|
4d1316c440
arg: fix ASAN error on sampler_type_names empty (#18167)
|
1 month ago |
|
Pascal
|
6ce3d85796
server: (webui) add --webui-config (#18028)
|
1 month ago |
|
Pascal
|
487674fbb3
common: fix --override-kv to support comma-separated values (#18056)
|
1 month ago |
 TrevorS
|
4b2a4778f8
arg: allow -kvu flag for llama-perplexity (#18117)
|
1 month ago |
|
Xuan-Son Nguyen
|
7b1db3d3b7
arg: clarify auto kvu/np being set on server (#17997)
|
1 month ago |
|
Johannes Gäßler
|
b1f3a6e5db
llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization (#16653)
|
1 month ago |
 Georgi Gerganov
|
254098a279
common : refactor common_sampler + grammar logic changes (#17937)
|
1 month ago |
|
Xuan-Son Nguyen
|
4d5ae24c0a
arg: fix common_params_parse not accepting negated arg (#17991)
|
1 month ago |
