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

4
tools/server/tests/unit/test_completion.py
View File

@@ -16,7 +16,7 @@ def create_server():
@pytest.mark.parametrize("prompt,n_predict,re_content,n_prompt,n_predicted,truncated,return_tokens", [
("I believe the meaning of life is", 8, "(going|bed)+", 18, 8, False, False),
("Write a joke about AI from a very long prompt which will not be truncated", 256, "(princesses|everyone|kids|Anna|forest)+", 46, 64, False, True),
("Write a joke about AI from a very long prompt which will not be truncated", 64, "(princesses|everyone|kids|Anna|forest)+", 46, 64, False, True),
])
def test_completion(prompt: str, n_predict: int, re_content: str, n_prompt: int, n_predicted: int, truncated: bool, return_tokens: bool):
global server
@@ -41,7 +41,7 @@ def test_completion(prompt: str, n_predict: int, re_content: str, n_prompt: int,
@pytest.mark.parametrize("prompt,n_predict,re_content,n_prompt,n_predicted,truncated", [
("I believe the meaning of life is", 8, "(going|bed)+", 18, 8, False),
("Write a joke about AI from a very long prompt which will not be truncated", 256, "(princesses|everyone|kids|Anna|forest)+", 46, 64, False),
("Write a joke about AI from a very long prompt which will not be truncated", 64, "(princesses|everyone|kids|Anna|forest)+", 46, 64, False),
])
def test_completion_stream(prompt: str, n_predict: int, re_content: str, n_prompt: int, n_predicted: int, truncated: bool):
global server