[ci] refactor longtext benchmark #4087
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
lvhan028
reviewed
Nov 2, 2025
Comment on lines
+21
to
+26
| turbomind_chat_model: | ||
| - Qwen/Qwen3-30B-A3B | ||
| - Qwen/Qwen3-235B-A22B | ||
| - Qwen/Qwen3-32B | ||
| - Qwen/Qwen3-8B | ||
| - Qwen/Qwen3-0.6B |
There was a problem hiding this comment.
turbomind doesn't support ascend
lvhan028
reviewed
Nov 2, 2025
Comment on lines
+36
to
+42
| turbomind_vl_model: | ||
| - internlm/Intern-S1 | ||
| - internlm/Intern-S1-mini | ||
| - OpenGVLab/InternVL3_5-2B | ||
| - OpenGVLab/InternVL3_5-8B | ||
| - OpenGVLab/InternVL3_5-38B | ||
|
|
There was a problem hiding this comment.
turbomind doesn't support ascend
lvhan028
reviewed
Nov 2, 2025
Comment on lines
+51
to
+53
| turbomind_base_model: | ||
| - Qwen/Qwen3-0.6B | ||
|
|
There was a problem hiding this comment.
turbomind doesn't support ascend
lvhan028
reviewed
Nov 2, 2025
Comment on lines
+57
to
+94
| turbomind_quatization: | ||
| no_awq: | ||
| - Qwen/Qwen3-30B-A3B | ||
| - Qwen/Qwen3-235B-A22B | ||
| - Qwen/Qwen3-32B | ||
| - Qwen/Qwen3-8B | ||
| - Qwen/Qwen3-0.6B | ||
| - internlm/Intern-S1 | ||
| - internlm/Intern-S1-mini | ||
| - OpenGVLab/InternVL3_5-2B | ||
| - OpenGVLab/InternVL3_5-8B | ||
| - OpenGVLab/InternVL3_5-38B | ||
|
|
||
| gptq: | ||
| - Empty | ||
| no_kvint4: | ||
| - Qwen/Qwen3-30B-A3B | ||
| - Qwen/Qwen3-235B-A22B | ||
| - Qwen/Qwen3-32B | ||
| - Qwen/Qwen3-8B | ||
| - Qwen/Qwen3-0.6B | ||
| - internlm/Intern-S1 | ||
| - internlm/Intern-S1-mini | ||
| - OpenGVLab/InternVL3_5-2B | ||
| - OpenGVLab/InternVL3_5-8B | ||
| - OpenGVLab/InternVL3_5-38B | ||
| no_kvint8: | ||
| - Qwen/Qwen3-30B-A3B | ||
| - Qwen/Qwen3-235B-A22B | ||
| - Qwen/Qwen3-32B | ||
| - Qwen/Qwen3-8B | ||
| - Qwen/Qwen3-0.6B | ||
| - internlm/Intern-S1 | ||
| - internlm/Intern-S1-mini | ||
| - OpenGVLab/InternVL3_5-2B | ||
| - OpenGVLab/InternVL3_5-8B | ||
| - OpenGVLab/InternVL3_5-38B | ||
|
|
There was a problem hiding this comment.
turbomind doesn't support ascend
lvhan028
reviewed
Nov 2, 2025
Comment on lines
+65
to
+69
| turbomind_base_model: | ||
| - internlm/Intern-S1-mini | ||
| - Qwen/Qwen3-4B-FP8 | ||
| - openai/gpt-oss-20b | ||
|
|
There was a problem hiding this comment.
Those models are not base model
lvhan028
reviewed
Nov 2, 2025
Comment on lines
-11
to
-42
| def command_line_test(config, | ||
| case, | ||
| case_info, | ||
| model_case, | ||
| type, | ||
| extra: str = None, | ||
| cuda_prefix: str = None, | ||
| worker_id: str = ''): | ||
| dst_path = config.get('dst_path') | ||
|
|
||
| cmd = get_command_with_extra('lmdeploy chat ' + dst_path + '/workspace_' + model_case, | ||
| config, | ||
| model_case, | ||
| cuda_prefix=cuda_prefix) | ||
| if type == 'turbomind': | ||
| if ('w4' in model_case or ('4bits' in model_case or 'awq' in model_case.lower())): | ||
| cmd += ' --model-format awq' | ||
| elif 'gptq' in model_case.lower(): | ||
| cmd += ' --model-format gptq' | ||
| if case == 'base_testcase': | ||
| cmd += ' --chat-template ' + TEMPLATE | ||
|
|
||
| # Add device option if specified in environment | ||
| device = os.environ.get('DEVICE', '') | ||
| if device: | ||
| cmd += f' --device {device} ' | ||
| if device == 'ascend': | ||
| cmd += '--eager-mode ' | ||
|
|
||
| return command_test(config, [cmd], model_case, case, case_info, type == 'turbomind', worker_id=worker_id) | ||
|
|
||
|
|
There was a problem hiding this comment.
No longer test the chat CLI?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.