Olivier Chafik
|
5b7b0ac8df
json-schema-to-grammar improvements (+ added to server) (#5978)
|
пре 1 година |
Karthick
|
47cc7a7bf9
Server: Handle n_keep parameter in the request (#6174)
|
пре 1 година |
Xuan Son Nguyen
|
99b71c068f
Server: Use multi-task for embeddings endpoint (#6001)
|
пре 1 година |
Xuan Son Nguyen
|
caa106d4e0
Server: format error to json (#5961)
|
пре 1 година |
Minsoo Cheong
|
332bdfd798
server : maintain chat completion id for streaming responses (#5988)
|
пре 1 година |
Georgi Gerganov
|
2002bc96bf
server : refactor (#5882)
|
пре 1 година |
Pierrick Hymbert
|
9731134296
server: tests: passkey challenge / self-extend with context shift demo (#5832)
|
пре 1 година |
Xuan Son Nguyen
|
052051d8ae
Server: normalize naming (#5779)
|
пре 1 година |
Pierrick Hymbert
|
930b178026
server: logs - unified format and --log-format option (#5700)
|
пре 1 година |
Pierrick Hymbert
|
d52d7819b8
server: concurrency fix + monitoring - add /metrics prometheus compatible endpoint (#5708)
|
пре 1 година |
Pierrick Hymbert
|
1ecea255eb
server: health: fix race condition on slots data using tasks queue (#5634)
|
пре 1 година |
Xuan Son Nguyen
|
9c405c9f9a
Server: use llama_chat_apply_template (#5593)
|
пре 1 година |
Daniel Hiltgen
|
66c1968f7a
server : graceful server shutdown (#5244)
|
пре 1 година |
Xuan Son Nguyen
|
907e08c110
server : add llama2 chat template (#5425)
|
пре 1 година |
Georgi Gerganov
|
753eafed0e
sync : ggml
|
пре 2 година |
Xuan Son Nguyen
|
48c857aa10
server : refactored the task processing logic (#5065)
|
пре 2 година |