[Bugfix][Model] Fix fusedmoe and make modelrunner_v1 compatible with latest vllm #867
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
Signed-off-by: MengqingCao <cmq0113@163.com>
Signed-off-by: MengqingCao <cmq0113@163.com>
wangxiyuan
reviewed
May 15, 2025
| max_model_len=self.max_model_len, | ||
| max_num_batched_tokens=self.max_num_tokens, | ||
| device=self.device, | ||
| pin_memory=self.pin_memory, |
| cache_config.cache_dtype] | ||
|
|
||
| self.attn_metadata_builders: list[AscendAttentionMetadataBuilder] = [] | ||
| self.attn_backends: list[type[AscendAttentionBackend]] = [] |
| self.scheduler_config = vllm_config.scheduler_config | ||
| self.chunked_prefill_enabled = vllm_config.scheduler_config.chunked_prefill_enabled | ||
| self.device = device | ||
| self.pin_memory = True |
|
|
||
| self.is_multimodal_model = self.model_config.is_multimodal_model | ||
| self.block_size = vllm_config.cache_config.block_size | ||
| self.max_model_len = self.model_config.max_model_len |
There was a problem hiding this comment.
useless, use self.model_config.max_model_len for InputBatch
Signed-off-by: MengqingCao <cmq0113@163.com>
Signed-off-by: MengqingCao <cmq0113@163.com>
wangxiyuan
approved these changes
May 15, 2025
|
LGTM. let's merge this to unblock CI once the CI passed. Thanks for the fix. |
Signed-off-by: MengqingCao <cmq0113@163.com>
Thanks, I make a small change in the latest commit, plz help to review it. |
MengqingCao
changed the title
ApsarasX
reviewed
May 16, 2025
| self.local_num_experts = self.global_num_experts | ||
| self.expert_map = None | ||
|
|
||
| if vllm_version_is("0.8.5") or vllm_version_is("0.8.5.post1"): |
There was a problem hiding this comment.
I think this part of the code may not be needed, refer to the modification of this part in PR 863
However, the most urgent thing at present is to fix CI, which can be considered later
There was a problem hiding this comment.
yes let' make ci happy first then solve the bug later
ApsarasX
approved these changes
May 16, 2025
chopper0126
pushed a commit
to chopper0126/vllm-ascend
that referenced
this pull request
Oct 16, 2025
…latest vllm (vllm-project#867) ### What this PR does / why we need it? this PR fix CI failure broken by vllm. 1. add moe_config for fused_moe 2. adjust the change for kv cache group from vllm. currently vllm-ascend doesn't support this feature. this is just a quick fix for backward compatibility fix: vllm-project#872 --------- Signed-off-by: MengqingCao <cmq0113@163.com>
Angazenn
pushed a commit
to Angazenn/vllm-ascend
that referenced
this pull request
Oct 21, 2025
…latest vllm (vllm-project#867) ### What this PR does / why we need it? this PR fix CI failure broken by vllm. 1. add moe_config for fused_moe 2. adjust the change for kv cache group from vllm. currently vllm-ascend doesn't support this feature. this is just a quick fix for backward compatibility fix: vllm-project#872 --------- Signed-off-by: MengqingCao <cmq0113@163.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 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.
What this PR does / why we need it?
this PR fix CI failure broken by vllm.
fix: #872