Georgi Gerganov 85a7d8677b memory : remove KV cache size padding (#16812) ...

* memory : remove KV cache size padding

* cont : restore padding for n_kv tensor shape

* server : use slot context size instead of training context size

* server : simplify context limit logic

2025-10-28 20:19:44 +02:00

..

test_basic.py

server : host-memory prompt caching (#16391)

2025-10-09 18:54:51 +03:00

test_chat_completion.py

server : return HTTP 400 if prompt exceeds context length (#16486)

2025-10-10 16:11:07 +02:00

test_completion.py

server : host-memory prompt caching (#16391)

2025-10-09 18:54:51 +03:00

test_ctx_shift.py

memory : remove KV cache size padding (#16812)

2025-10-28 20:19:44 +02:00

test_embedding.py

server : disable context shift by default (#15416)

2025-08-19 16:46:37 +03:00

test_infill.py

server : disable context shift by default (#15416)

2025-08-19 16:46:37 +03:00

test_lora.py

server : disable context shift by default (#15416)

2025-08-19 16:46:37 +03:00

test_rerank.py

server / ranking : add sorting and management of top_n (#16403)

2025-10-11 16:39:04 +03:00

test_security.py

server : disable context shift by default (#15416)

2025-08-19 16:46:37 +03:00

test_slot_save.py

server : disable context shift by default (#15416)

2025-08-19 16:46:37 +03:00

test_speculative.py

llama: use FA + max. GPU layers by default (#15434)

2025-08-30 16:32:10 +02:00

test_template.py

server : speed up tests (#15836)

2025-09-06 14:45:24 +02:00

test_tokenize.py

server : disable context shift by default (#15416)

2025-08-19 16:46:37 +03:00

test_tool_call.py

server : speed up tests (#15836)

2025-09-06 14:45:24 +02:00

test_vision_api.py

server : speed up tests (#15836)

2025-09-06 14:45:24 +02:00