CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

server: add exceed_context_size_error type (#15780)

Browse Source 
* server: add exceed_context_size_error type

* change error code to 400
This commit is contained in:
Xuan-Son Nguyen
2025-09-04 11:50:23 +02:00
committed by GitHub
parent badb80cadb
commit a68d914426
2 changed files with 45 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
tools/server/tests/unit/test_chat_completion.py
View File

@@ -385,3 +385,20 @@ def test_logit_bias():
output_text = res.choices[0].message.content
assert output_text
assert all(output_text.find(" " + tok + " ") == -1 for tok in exclude)
def test_context_size_exceeded():
global server
server.start()
res = server.make_request("POST", "/chat/completions", data={
"messages": [
{"role": "system", "content": "Book"},
{"role": "user", "content": "What is the best book"},
] * 100, # make the prompt too long
})
assert res.status_code == 400
assert "error" in res.body
assert res.body["error"]["type"] == "exceed_context_size_error"
assert res.body["error"]["n_prompt_tokens"] > 0
assert server.n_ctx is not None
assert server.n_slots is not None
assert res.body["error"]["n_ctx"] == server.n_ctx // server.n_slots