Gabe Goodhart
|
e1fa9569ba
server : add SSL support (#5926)
|
1 jaar geleden |
Pierrick Hymbert
|
fd72d2d2a5
server: tests: add truncated prompt tests, better kv cache size (#5933)
|
1 jaar geleden |
compilade
|
c2101a2e90
llama : support Mamba Selective State Space Models (#5328)
|
1 jaar geleden |
Pierrick Hymbert
|
76e868821a
server: metrics: add llamacpp:prompt_seconds_total and llamacpp:tokens_predicted_seconds_total, reset bucket only on /metrics. Fix values cast to int. Add Process-Start-Time-Unix header. (#5937)
|
1 jaar geleden |
Georgi Gerganov
|
af37fd8b30
server : fix EOS token detection with disabled cache (#5938)
|
1 jaar geleden |
Minsoo Cheong
|
55a2a900ff
server : add `/v1/completions` endpoint (#5914)
|
1 jaar geleden |
Georgi Gerganov
|
2002bc96bf
server : refactor (#5882)
|
1 jaar geleden |
Georgi Gerganov
|
29ae62d2ae
llama : fix embeddings (#5796)
|
1 jaar geleden |
Xuan Son Nguyen
|
4ffcdce2ff
add alias for chat template (#5858)
|
1 jaar geleden |
Pierrick Hymbert
|
8ef969afce
server : init http requests thread pool with --parallel if set (#5836)
|
1 jaar geleden |
Pierrick Hymbert
|
9731134296
server: tests: passkey challenge / self-extend with context shift demo (#5832)
|
1 jaar geleden |
Pierrick Hymbert
|
3ab8b3a92e
llama : cleanup unused mmq flags (#5772)
|
1 jaar geleden |
Pierrick Hymbert
|
5cb02b4a01
server: allow to override threads server pool with --threads-http (#5794)
|
1 jaar geleden |
Georgi Gerganov
|
f105471ef6
server : fix newlines in help (#5785)
|
1 jaar geleden |
Xuan Son Nguyen
|
052051d8ae
Server: normalize naming (#5779)
|
1 jaar geleden |
Xuan Son Nguyen
|
a693bea1e6
server : hit Ctrl+C twice to exit (#5734)
|
1 jaar geleden |
Jorge A
|
efc72253f7
server : add "/chat/completions" alias for "/v1/...` (#5722)
|
1 jaar geleden |
Xuan Son Nguyen
|
b11a93df41
fix server hangs on empty prompt (#5733)
|
1 jaar geleden |
Georgi Gerganov
|
bf08e00643
llama : refactor k-shift implementation + KV defragmentation (#5691)
|
1 jaar geleden |
compilade
|
f7625019c5
server : fix crash when system prompt is bigger than batch size (#5714)
|
1 jaar geleden |
Pierrick Hymbert
|
930b178026
server: logs - unified format and --log-format option (#5700)
|
1 jaar geleden |
Pierrick Hymbert
|
d52d7819b8
server: concurrency fix + monitoring - add /metrics prometheus compatible endpoint (#5708)
|
1 jaar geleden |
Georgi Gerganov
|
ab336a9d5e
code : normalize enum names (#5697)
|
1 jaar geleden |
Pierrick Hymbert
|
9e359a4f47
server: continue to update other slots on embedding concurrent request (#5699)
|
1 jaar geleden |
Pierrick Hymbert
|
525213d2f5
server: init functional tests (#5566)
|
1 jaar geleden |
AlpinDale
|
fd43d66f46
server : add KV cache quantization options (#5684)
|
1 jaar geleden |
Xuan Son Nguyen
|
a46f50747b
server : fallback to chatml, add AlphaMonarch chat template (#5628)
|
1 jaar geleden |
Jared Van Bortel
|
89febfed93
examples : do not assume BOS when shifting context (#5622)
|
1 jaar geleden |
Pierrick Hymbert
|
1ecea255eb
server: health: fix race condition on slots data using tasks queue (#5634)
|
1 jaar geleden |
CJ Pais
|
6560bed3f0
server : support llava 1.6 (#5553)
|
1 jaar geleden |