| .. |
|
test_basic.py
|
ddf9f94389
server : add Anthropic Messages API support (#17570)
|
1 bulan lalu |
|
test_chat_completion.py
|
5d6bd842ea
server: remove default "gpt-3.5-turbo" model name (#17668)
|
1 bulan lalu |
|
test_compat_anthropic.py
|
ddf9f94389
server : add Anthropic Messages API support (#17570)
|
1 bulan lalu |
|
test_completion.py
|
cb1adf8851
server : handle failures to restore host cache (#17078)
|
2 bulan lalu |
|
test_ctx_shift.py
|
85a7d8677b
memory : remove KV cache size padding (#16812)
|
2 bulan lalu |
|
test_embedding.py
|
d2fcd91cf9
server : disable context shift by default (#15416)
|
5 bulan lalu |
|
test_infill.py
|
cd5e3b5754
server : support unified cache across slots (#16736)
|
2 bulan lalu |
|
test_lora.py
|
d2fcd91cf9
server : disable context shift by default (#15416)
|
5 bulan lalu |
|
test_rerank.py
|
31d0ff1869
server / ranking : add sorting and management of top_n (#16403)
|
3 bulan lalu |
|
test_router.py
|
ec18edfcba
server: introduce API for serving / loading / unloading multiple models (#17470)
|
1 bulan lalu |
|
test_security.py
|
ddf9f94389
server : add Anthropic Messages API support (#17570)
|
1 bulan lalu |
|
test_slot_save.py
|
d2fcd91cf9
server : disable context shift by default (#15416)
|
5 bulan lalu |
|
test_speculative.py
|
16bcc1259d
kv-cache : pad the cache size to 256 for performance (#17046)
|
2 bulan lalu |
|
test_template.py
|
3c3635d2f2
server : speed up tests (#15836)
|
4 bulan lalu |
|
test_tokenize.py
|
d2fcd91cf9
server : disable context shift by default (#15416)
|
5 bulan lalu |
|
test_tool_call.py
|
3c3635d2f2
server : speed up tests (#15836)
|
4 bulan lalu |
|
test_vision_api.py
|
3c3635d2f2
server : speed up tests (#15836)
|
4 bulan lalu |
Xuan-Son Nguyen
5d6bd842ea
server: remove default "gpt-3.5-turbo" model name (#17668)