tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-01 21:15:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

server: streaming of tool calls and thoughts when --jinja is on (#12379)

Browse Source 
* add common_json w/ support for truncated json healing

* add common_chat_msg_diff

* partial common_chat_parse

* refactor parser w/ optionals

* server: wire chat diffs in stream mode

* fix trigger of thinking models (must happen after thoughts are closed)

* fix functionary v3.2 raw python!

* rename: common_chat_syntax (now contains format)

* rm common_regex.at_start

* don't return empty <think></think>

* accommodate yet another deepseek r1 distill fantasy syntax (`<｜tool▁calls｜>`)

* fix QwQ 32B tool call parsing after thoughts (hermes2)

* better logs for grammar triggers

* consume spaces after parse_json_tool_calls

* fix required tool calls w/ thinking models that have pre-opened thinking tags

* fix thinking model's initial trigger + test qwq's template

* run most test_tool_call tests in stream + non-stream modes

* make functionary v3.2 parsing more strict (differentiate first match from others)

* send final diff from server, to close off raw python arguments

* support partial content streaming in Generic mode

* tool-call: allow content prelude before hermes2 tool calls (for Qwen2.5)

* Update function-calling.md

* Update tool_bench.py

* chat-parser: remove input from exception (llm output may contain PII)

---------

Co-authored-by: ochafik <ochafik@google.com>
Co-authored-by: Olivier Chafik <ochafik@users.noreply.github.com>
This commit is contained in:
Olivier Chafik
2025-05-25 01:48:08 +01:00
committed by GitHub
parent a2d02d5793
commit f5cd27b71d
23 changed files with 3245 additions and 1091 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
tools/server/tests/unit/test_chat_completion.py
View File

@ -75,7 +75,7 @@ def test_chat_completion_stream(system_prompt, user_prompt, max_tokens, re_conte
choice = data["choices"][0]
if i == 0:
# Check first role message for stream=True
assert choice["delta"]["content"] == ""
assert choice["delta"]["content"] is None
assert choice["delta"]["role"] == "assistant"
else:
assert "role" not in choice["delta"]
@ -92,7 +92,7 @@ def test_chat_completion_stream(system_prompt, user_prompt, max_tokens, re_conte
assert choice["finish_reason"] == finish_reason
else:
assert choice["finish_reason"] is None
content += choice["delta"]["content"]
content += choice["delta"]["content"] or ''
def test_chat_completion_with_openai_library():
@ -251,8 +251,9 @@ def test_chat_completion_with_timings_per_token():
for i, data in enumerate(res):
if i == 0:
# Check first role message for stream=True
assert data["choices"][0]["delta"]["content"] == ""
assert data["choices"][0]["delta"]["content"] is None
assert data["choices"][0]["delta"]["role"] == "assistant"
assert "timings" not in data, f'First event should not have timings: {data}'
else:
assert "role" not in data["choices"][0]["delta"]
assert "timings" in data
@ -311,7 +312,7 @@ def test_logprobs_stream():
choice = data.choices[0]
if i == 0:
# Check first role message for stream=True
assert choice.delta.content == ""
assert choice.delta.content is None
assert choice.delta.role == "assistant"
else:
assert choice.delta.role is None