| .. |
|
test_basic.py
|
d00cbea63c
server : host-memory prompt caching (#16391)
|
il y a 3 mois |
|
test_chat_completion.py
|
cd5e3b5754
server : support unified cache across slots (#16736)
|
il y a 2 mois |
|
test_completion.py
|
cd5e3b5754
server : support unified cache across slots (#16736)
|
il y a 2 mois |
|
test_ctx_shift.py
|
85a7d8677b
memory : remove KV cache size padding (#16812)
|
il y a 2 mois |
|
test_embedding.py
|
d2fcd91cf9
server : disable context shift by default (#15416)
|
il y a 5 mois |
|
test_infill.py
|
cd5e3b5754
server : support unified cache across slots (#16736)
|
il y a 2 mois |
|
test_lora.py
|
d2fcd91cf9
server : disable context shift by default (#15416)
|
il y a 5 mois |
|
test_rerank.py
|
31d0ff1869
server / ranking : add sorting and management of top_n (#16403)
|
il y a 3 mois |
|
test_security.py
|
d2fcd91cf9
server : disable context shift by default (#15416)
|
il y a 5 mois |
|
test_slot_save.py
|
d2fcd91cf9
server : disable context shift by default (#15416)
|
il y a 5 mois |
|
test_speculative.py
|
e81b8e4b7f
llama: use FA + max. GPU layers by default (#15434)
|
il y a 4 mois |
|
test_template.py
|
3c3635d2f2
server : speed up tests (#15836)
|
il y a 4 mois |
|
test_tokenize.py
|
d2fcd91cf9
server : disable context shift by default (#15416)
|
il y a 5 mois |
|
test_tool_call.py
|
3c3635d2f2
server : speed up tests (#15836)
|
il y a 4 mois |
|
test_vision_api.py
|
3c3635d2f2
server : speed up tests (#15836)
|
il y a 4 mois |
Georgi Gerganov
cd5e3b5754
server : support unified cache across slots (#16736)