| .. |
|
test_basic.py
|
e7c2cf1356
server: add router multi-model tests (#17704) (#17722)
|
пре 1 месец |
|
test_chat_completion.py
|
f5f8812f7c
server : use different seeds for child completions (#18700)
|
пре 3 недеља |
|
test_compat_anthropic.py
|
3d26a09dc7
server : add thinking content blocks to Anthropic Messages API (#18551)
|
пре 3 недеља |
|
test_completion.py
|
f307926482
server : adjust unified KV cache tests (#18716)
|
пре 2 недеља |
|
test_ctx_shift.py
|
85a7d8677b
memory : remove KV cache size padding (#16812)
|
пре 3 месеци |
|
test_embedding.py
|
d2fcd91cf9
server : disable context shift by default (#15416)
|
пре 5 месеци |
|
test_infill.py
|
cd5e3b5754
server : support unified cache across slots (#16736)
|
пре 2 месеци |
|
test_lora.py
|
d2fcd91cf9
server : disable context shift by default (#15416)
|
пре 5 месеци |
|
test_rerank.py
|
31d0ff1869
server / ranking : add sorting and management of top_n (#16403)
|
пре 3 месеци |
|
test_router.py
|
e7c2cf1356
server: add router multi-model tests (#17704) (#17722)
|
пре 1 месец |
|
test_security.py
|
13628d8bdb
server: add --media-path for local media files (#17697)
|
пре 1 месец |
|
test_sleep.py
|
ddcb75dd8a
server: add auto-sleep after N seconds of idle (#18228)
|
пре 1 месец |
|
test_slot_save.py
|
d2fcd91cf9
server : disable context shift by default (#15416)
|
пре 5 месеци |
|
test_speculative.py
|
16bcc1259d
kv-cache : pad the cache size to 256 for performance (#17046)
|
пре 2 месеци |
|
test_template.py
|
3c3635d2f2
server : speed up tests (#15836)
|
пре 4 месеци |
|
test_tokenize.py
|
d2fcd91cf9
server : disable context shift by default (#15416)
|
пре 5 месеци |
|
test_tool_call.py
|
3c3635d2f2
server : speed up tests (#15836)
|
пре 4 месеци |
|
test_vision_api.py
|
3c3635d2f2
server : speed up tests (#15836)
|
пре 4 месеци |
Georgi Gerganov
f307926482
server : adjust unified KV cache tests (#18716)