Reza Rahemtola
|
c1f958c038
server : (docs) Update wrong tool calling example (#11809)
|
11 mesiacov pred |
Olivier Chafik
|
c7f460ab88
`server`: fix tool-call of DeepSeek R1 Qwen, return reasoning_content (Command 7RB & DeepSeek R1) unless `--reasoning-format none` (#11607)
|
11 mesiacov pred |
Nikolaos Pothitos
|
3ab410f55f
readme : update front-end framework (#11753)
|
11 mesiacov pred |
Olivier Chafik
|
bfcce4d693
`tool-call`: support Command R7B (+ return tool_plan "thoughts" in API) (#11585)
|
11 mesiacov pred |
Olivier Chafik
|
a83f528688
`tool-call`: fix llama 3.x and functionary 3.2, play nice w/ pydantic_ai package, update readme (#11539)
|
11 mesiacov pred |
Olivier Chafik
|
8b576b6c55
Tool call support (generic + native for Llama, Functionary, Hermes, Mistral, Firefunction, DeepSeek) w/ lazy grammars (#9639)
|
11 mesiacov pred |
Isaac McFadyen
|
496e5bf46b
server : (docs) added response format for /apply-template [no ci] (#11503)
|
11 mesiacov pred |
Daniel Bevenius
|
e0449763a4
server : update json snippets in README.md [no ci] (#11492)
|
11 mesiacov pred |
Nigel Bosch
|
eb7cf15a80
server : add /apply-template endpoint for additional use cases of Minja functionality (#11489)
|
11 mesiacov pred |
Daniel Bevenius
|
e51c47b401
server : update auto gen files comments [no ci] (#11484)
|
11 mesiacov pred |
Olivier Chafik
|
6171c9d258
Add Jinja template support (#11016)
|
1 rok pred |
Georgi Gerganov
|
a3c1232c3f
arg : option to exclude arguments from specific examples (#11136)
|
1 rok pred |
Xuan Son Nguyen
|
0da5d86026
server : allow using LoRA adapters per-request (#10994)
|
1 rok pred |
Xuan Son Nguyen
|
5896c65232
server : add OAI compat for /v1/completions (#10974)
|
1 rok pred |
Isaac McFadyen
|
f865ea149d
server: added more docs for response_fields field (#10995)
|
1 rok pred |
NeverLucky
|
09fe2e7613
server: allow filtering llama server response fields (#10940)
|
1 rok pred |
Xuan Son Nguyen
|
485dc01214
server : add system_fingerprint to chat/completion (#10917)
|
1 rok pred |
Xuan Son Nguyen
|
57bb2c40cd
server : fix logprobs, make it OAI-compatible (#10783)
|
1 rok pred |
Georgi Gerganov
|
152610eda9
server : output embeddings for all tokens when pooling = none (#10861)
|
1 rok pred |
Georgi Gerganov
|
0e70ba686e
server : add "tokens" output (#10853)
|
1 rok pred |
Georgi Gerganov
|
644fd71b44
sampling : refactor + optimize penalties sampler (#10803)
|
1 rok pred |
Xuan Son Nguyen
|
adffa6ffd5
common : improve -ctv -ctk CLI arguments (#10806)
|
1 rok pred |
CentricStorm
|
5555c0c1f6
docs: update server streaming mode documentation (#9519)
|
1 rok pred |
CentricStorm
|
4b4d92b098
docs: fix server documentation formatting (#10776)
|
1 rok pred |
Yüg
|
a86ad841f1
server : add flag to disable the web-ui (#10762) (#10751)
|
1 rok pred |
Xuan Son Nguyen
|
3573fa8e7b
server : (refactor) no more json in server_task input (#10691)
|
1 rok pred |
Georgi Gerganov
|
ce4a7b8493
server : various fixes (#10704)
|
1 rok pred |
Xuan Son Nguyen
|
6c5bc0625f
server : (refactoring) do not rely on JSON internally (#10643)
|
1 rok pred |
Xuan Son Nguyen
|
91c36c269b
server : (web ui) Various improvements, now use vite as bundler (#10599)
|
1 rok pred |
Nikolaos Pothitos
|
82bca2257b
readme : add option, update default value, fix formatting (#10271)
|
1 rok pred |