| .. |
|
test_basic.py
|
d2fcd91cf9
server : disable context shift by default (#15416)
|
hai 5 meses |
|
test_chat_completion.py
|
a68d914426
server: add exceed_context_size_error type (#15780)
|
hai 4 meses |
|
test_completion.py
|
4afb0a746f
server : Support multimodal completion and embeddings prompts in JSON format (#15108)
|
hai 5 meses |
|
test_ctx_shift.py
|
e81b8e4b7f
llama: use FA + max. GPU layers by default (#15434)
|
hai 4 meses |
|
test_embedding.py
|
d2fcd91cf9
server : disable context shift by default (#15416)
|
hai 5 meses |
|
test_infill.py
|
d2fcd91cf9
server : disable context shift by default (#15416)
|
hai 5 meses |
|
test_lora.py
|
d2fcd91cf9
server : disable context shift by default (#15416)
|
hai 5 meses |
|
test_rerank.py
|
d2fcd91cf9
server : disable context shift by default (#15416)
|
hai 5 meses |
|
test_security.py
|
d2fcd91cf9
server : disable context shift by default (#15416)
|
hai 5 meses |
|
test_slot_save.py
|
d2fcd91cf9
server : disable context shift by default (#15416)
|
hai 5 meses |
|
test_speculative.py
|
e81b8e4b7f
llama: use FA + max. GPU layers by default (#15434)
|
hai 4 meses |
|
test_template.py
|
e121edc432
`server`: add `--reasoning-budget 0` to disable thinking (incl. qwen3 w/ enable_thinking:false) (#13771)
|
hai 8 meses |
|
test_tokenize.py
|
d2fcd91cf9
server : disable context shift by default (#15416)
|
hai 5 meses |
|
test_tool_call.py
|
d2fcd91cf9
server : disable context shift by default (#15416)
|
hai 5 meses |
|
test_vision_api.py
|
4afb0a746f
server : Support multimodal completion and embeddings prompts in JSON format (#15108)
|
hai 5 meses |
Xuan-Son Nguyen
a68d914426
server: add exceed_context_size_error type (#15780)