mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2026-05-03 06:00:31 +00:00
server : support unified cache across slots (#16736)
* server : support unified context across slots * cont : fix speculative decoding initialization * context : fix n_ctx_per_seq computation * server : purge slots one by one * tests : add unified cache server tests * llama : update per-seq context computation * test-thread-safety : handle tiny training context of the input model * server : fix server_tokens clear() * server : use 4 slots + unified KV by default * llama : add note about context size queries * cont : update todos [no ci] * context : do not cap the size of the context * tests : adjust parameters to be CI friendlier * context : add warning
This commit is contained in:
parent
87c9efc3b2
commit
cd5e3b5754
12 changed files with 163 additions and 48 deletions
|
|
@ -18,7 +18,7 @@ def test_infill_without_input_extra():
|
|||
"input_suffix": "}\n",
|
||||
})
|
||||
assert res.status_code == 200
|
||||
assert match_regex("(Ann|small|shiny|Daddy)+", res.body["content"])
|
||||
assert match_regex("(Ann|small|shiny|Daddy|Jimmy)+", res.body["content"])
|
||||
|
||||
|
||||
def test_infill_with_input_extra():
|
||||
|
|
@ -34,7 +34,7 @@ def test_infill_with_input_extra():
|
|||
"input_suffix": "}\n",
|
||||
})
|
||||
assert res.status_code == 200
|
||||
assert match_regex("(Dad|excited|park)+", res.body["content"])
|
||||
assert match_regex("(Dad|excited|park|Jimmy)+", res.body["content"])
|
||||
|
||||
|
||||
@pytest.mark.parametrize("input_extra", [
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue