CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-29 08:41:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : host-memory prompt caching (#16391)

Browse Source 
* minor : code style

* server : fix prompt similarity calculation

* server : initial host-memory prompt caching

* cont

* server : refactor

* cont

* cont : make the server task of the slot const

* cont : minor [no ci]

* server : cache prompts and checkpoints only for completion tasks

* server : improve prompt caching logic

* cont : fix check for number of cached prompts [no ci]

* server : improve caching logic, add -cram CLI arg

* server : print prompt mismatch info

* cont : better naming [no ci]

* server : improve prompt cache loading logic

* server : add option to debug the slot contents (#16482)

* server : add option to debug the slot contents

* Update tools/server/server.cpp

---------

Co-authored-by: Xuan-Son Nguyen <son@huggingface.co>

* server : add option to disable prompt cache

---------

Co-authored-by: Xuan-Son Nguyen <son@huggingface.co>
This commit is contained in:
Georgi Gerganov
2025-10-09 18:54:51 +03:00
committed by GitHub
parent 8328fd4bae
commit d00cbea63c
10 changed files with 813 additions and 471 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tools/server/tests/unit/test_chat_completion.py
View File

@@ -19,8 +19,8 @@ def create_server():
(None, "Book", "What is the best book", 8, "(Suddenly)+|\\{ \" Sarax.", 77, 8, "length", True, None),
(None, "Book", "What is the best book", 8, "(Suddenly)+|\\{ \" Sarax.", 77, 8, "length", True, 'chatml'),
(None, "Book", "What is the best book", 8, "^ blue", 23, 8, "length", True, "This is not a chat template, it is"),
("codellama70b", "You are a coding assistant.", "Write the fibonacci function in c++.", 128, "(Aside|she|felter|alonger)+", 104, 64, "length", False, None),
("codellama70b", "You are a coding assistant.", "Write the fibonacci function in c++.", 128, "(Aside|she|felter|alonger)+", 104, 64, "length", True, None),
("codellama70b", "You are a coding assistant.", "Write the fibonacci function in c++.", 128, "(Aside|she|felter|alonger)+", 104, 128, "length", False, None),
("codellama70b", "You are a coding assistant.", "Write the fibonacci function in c++.", 128, "(Aside|she|felter|alonger)+", 104, 128, "length", True, None),
(None, "Book", [{"type": "text", "text": "What is"}, {"type": "text", "text": "the best book"}], 8, "Whillicter", 79, 8, "length", False, None),
(None, "Book", [{"type": "text", "text": "What is"}, {"type": "text", "text": "the best book"}], 8, "Whillicter", 79, 8, "length", True, None),
]
@@ -54,7 +54,7 @@ def test_chat_completion(model, system_prompt, user_prompt, max_tokens, re_conte
"system_prompt,user_prompt,max_tokens,re_content,n_prompt,n_predicted,finish_reason",
[
("Book", "What is the best book", 8, "(Suddenly)+", 77, 8, "length"),
("You are a coding assistant.", "Write the fibonacci function in c++.", 128, "(Aside|she|felter|alonger)+", 104, 64, "length"),
("You are a coding assistant.", "Write the fibonacci function in c++.", 128, "(Aside|she|felter|alonger)+", 104, 128, "length"),
]
)
def test_chat_completion_stream(system_prompt, user_prompt, max_tokens, re_content, n_prompt, n_predicted, finish_reason):