huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 12:24:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: skip long runnning tests

Browse Source
This commit is contained in:
drbh 2024-03-01 04:38:34 +00:00
parent 1eff07c0e4
commit 57a5766848
3 changed files with 9 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
integration-tests/models/test_flash_grammar_llama.py
View File

@ -28,6 +28,7 @@ async def test_flash_llama_grammar(flash_llama_grammar, response_snapshot):
assert response == response_snapshot
@pytest.mark.skip
@pytest.mark.asyncio
async def test_flash_llama_grammar_regex(flash_llama_grammar, response_snapshot):
response = await flash_llama_grammar.generate(
@ -46,6 +47,7 @@ async def test_flash_llama_grammar_regex(flash_llama_grammar, response_snapshot)
assert response == response_snapshot
@pytest.mark.skip
@pytest.mark.asyncio
async def test_flash_llama_grammar_json(flash_llama_grammar, response_snapshot):
response = await flash_llama_grammar.generate(
@ -94,6 +96,7 @@ async def test_flash_llama_grammar_json(flash_llama_grammar, response_snapshot):
assert response == response_snapshot
@pytest.mark.skip
@pytest.mark.asyncio
async def test_flash_llama_grammar_load(
flash_llama_grammar, generate_load, response_snapshot
@ -125,6 +128,7 @@ async def test_flash_llama_grammar_load(
# this is the same as the above test, but only fires off a single request
# this is only to ensure that the parallel and single inference produce the same result
@pytest.mark.skip
@pytest.mark.asyncio
async def test_flash_llama_grammar_single_load_instance(
flash_llama_grammar, generate_load, response_snapshot

1
integration-tests/models/test_grammar_llama.py
View File

@ -21,6 +21,7 @@ async def non_flash_llama_grammar(non_flash_llama_grammar_handle):
return non_flash_llama_grammar_handle.client
@pytest.mark.skip
@pytest.mark.asyncio
async def test_non_flash_llama_grammar_json(non_flash_llama_grammar, response_snapshot):
response = await non_flash_llama_grammar.generate(

4
integration-tests/models/test_tools_llama.py
View File

@ -98,6 +98,7 @@ async def test_flash_llama_grammar_no_tools(
assert response == response_snapshot
@pytest.mark.skip
@pytest.mark.asyncio
@pytest.mark.private
async def test_flash_llama_grammar_tools(flash_llama_grammar_tools, response_snapshot):
@ -134,6 +135,7 @@ async def test_flash_llama_grammar_tools(flash_llama_grammar_tools, response_sna
assert response == response_snapshot
@pytest.mark.skip
@pytest.mark.asyncio
@pytest.mark.private
async def test_flash_llama_grammar_tools_auto(
@ -173,6 +175,7 @@ async def test_flash_llama_grammar_tools_auto(
assert response == response_snapshot
@pytest.mark.skip
@pytest.mark.asyncio
@pytest.mark.private
async def test_flash_llama_grammar_tools_choice(
@ -208,6 +211,7 @@ async def test_flash_llama_grammar_tools_choice(
assert response == response_snapshot
@pytest.mark.skip
@pytest.mark.asyncio
@pytest.mark.private
async def test_flash_llama_grammar_tools_stream(