mirror/OpenLLM
1
0
Fork 0
mirror of https://github.com/bentoml/OpenLLM.git synced 2026-02-24 02:39:28 -05:00
Code Issues Packages Projects Releases Wiki Activity

fix(awq): correct awq detection for support (#586)

Browse Source 
* fix(awq): correct detection for awq

Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>

* chore: update base docker to work

Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>

* chore: disable awq on pytorch for now

Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>

* ci: auto fixes from pre-commit.ci

For more information, see https://pre-commit.ci

---------

Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
Aaron Pham
2023-11-08 06:57:11 -05:00
committed by GitHub
parent 655a4071de
commit ff8b6377c8
7 changed files with 44 additions and 77 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
openllm-python/tests/conftest.py
View File

@@ -13,7 +13,7 @@ if t.TYPE_CHECKING:
_MODELING_MAPPING = {'flan_t5': 'google/flan-t5-small', 'opt': 'facebook/opt-125m', 'baichuan': 'baichuan-inc/Baichuan-7B'}
_PROMPT_MAPPING = {'qa': 'Answer the following yes/no question by reasoning step-by-step. Can you write a whole Haiku in a single tweet?'}
def parametrise_local_llm(model: str,) -> t.Generator[tuple[str, openllm.LLMRunner[t.Any, t.Any] | openllm.LLM[t.Any, t.Any]], None, None]:
def parametrise_local_llm(model: str) -> t.Generator[tuple[str, openllm.LLMRunner[t.Any, t.Any] | openllm.LLM[t.Any, t.Any]], None, None]:
if model not in _MODELING_MAPPING: pytest.skip(f"'{model}' is not yet supported in framework testing.")
backends: tuple[LiteralBackend, ...] = ('pt',)
for backend, prompt in itertools.product(backends, _PROMPT_MAPPING.keys()):