[Misc] Refactor additional_config (#1029)

More and more config options are added to additional_config. This PR
provide a new AscendConfig to manage these config options by an easier
way to make code cleaner and readable.

 This PR also added the `additional_config` doc for users.

Added the test_ascend_config.py to make sure the new AscendConfig works
as expect.

TODO: Add e2e test with torchair and deepseek once the CI resource is
available.

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2025-06-05 16:28:01 +08:00
committed by GitHub
parent 7737aaa40f
commit e1ab6d318e
23 changed files with 456 additions and 208 deletions

View File

@@ -167,17 +167,17 @@ def run_equality_correctness_test(
# TODO current torchair graph mode needs clean torchair cache.
# if do not clean, it will raise error
additional_config = common_llm_kwargs.get("additional_config")
enable_graph_mode = additional_config.get(
"enable_graph_mode") if additional_config else False
torchair_graph_enabled = common_llm_kwargs.get(
"additional_config", {}).get("torchair_graph_config",
{}).get("enabled", False)
with vllm_runner(**org_args) as vllm_model:
if enable_graph_mode:
if torchair_graph_enabled:
_clean_torchair_cache()
org_outputs = vllm_model.generate_w_logprobs(prompts, sampling_params)
with vllm_runner(**sd_args) as vllm_model:
if enable_graph_mode:
if torchair_graph_enabled:
_clean_torchair_cache()
if ensure_all_accepted or expected_acceptance_rate is not None:
# Force log interval to be 0 to catch all metrics.

View File

@@ -218,7 +218,9 @@ def test_mtp_e2e_greedy_logprobs(vllm_runner, common_llm_kwargs,
"common_llm_kwargs",
[{
"additional_config": {
'enable_graph_mode': True,
'torchair_graph_config': {
"enabled": True,
},
},
# Print spec metrics.
@@ -262,7 +264,9 @@ def test_mtp_e2e_greedy_correctness_torchair_graph(
"common_llm_kwargs",
[{
"additional_config": {
'enable_graph_mode': True,
'torchair_graph_config': {
"enabled": True,
},
},
# Print spec metrics.