[0.13.0][Bugfix] Fix setting of speculative_config.enforce_eager for dsv32#5958
Merged
yiz-liu merged 1 commit intovllm-project:releases/v0.13.0from Jan 21, 2026
Merged
Conversation
…r dsv32 Signed-off-by: Zetong Li <slippersss@126.com>
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request aims to fix an issue with speculative_config.enforce_eager being incorrectly forced for deepseek_v32 models on the Ascend platform, which supports graph mode. The change correctly overrides this setting. However, the implementation introduces a potential AttributeError that could lead to a crash. I have provided a critical-severity comment with a suggested code change to make the logic more robust and prevent this potential runtime error.
Comment on lines
+368
to
+372
| if model_config and speculative_config and \ | ||
| hasattr(model_config.hf_text_config, "model_type") and \ | ||
| model_config.hf_text_config.model_type == "deepseek_v32" and \ | ||
| speculative_config.enforce_eager: | ||
| speculative_config.enforce_eager = False |
Contributor
There was a problem hiding this comment.
The condition to check for the deepseek_v32 model type is not fully robust. It could raise an AttributeError if model_config.hf_text_config is None, which would cause the application to crash. It's safer to use getattr to access nested attributes with a default value to prevent such crashes. I've refactored the logic to be more robust and readable.
Suggested change
| if model_config and speculative_config and \ | |
| hasattr(model_config.hf_text_config, "model_type") and \ | |
| model_config.hf_text_config.model_type == "deepseek_v32" and \ | |
| speculative_config.enforce_eager: | |
| speculative_config.enforce_eager = False | |
| if model_config and speculative_config and speculative_config.enforce_eager: | |
| hf_text_config = getattr(model_config, "hf_text_config", None) | |
| if (hf_text_config and | |
| getattr(hf_text_config, "model_type", None) == "deepseek_v32"): | |
| speculative_config.enforce_eager = False |
yiz-liu
approved these changes
Jan 21, 2026
845473182
pushed a commit
to 845473182/vllm-ascend
that referenced
this pull request
Jan 21, 2026
…lm-ascend into FIA_v0.13.0 * 'releases/v0.13.0' of https://github.com/vllm-project/vllm-ascend: [0.13.0][Bugfix] Fix setting of `speculative_config.enforce_eager` for dsv32 (vllm-project#5958) [v0.13.0][Bugfix] Fix XliteModelRunner init failed when aclgraph is enabled (vllm-project#5887) [0.13.0][Bugfix] Fixed an problem related to embeddings sharing (vllm-project#5972) [Bugfix]Fixed precision issues caused by pooled request pooling (vllm-project#6057) [0.13.0][Bugfix] fix pcp aclgraph qwen FIA bug (vllm-project#6038) [0.13.0][cherry-pick][bugfix] fix bug of triton mrope (vllm-project#6009) 【0.13.0】【bugfix】Resolved memory deallocation failure in the pooling layer under re-computation workloads. (vllm-project#6056)
Mercykid-bash
pushed a commit
to Mercykid-bash/vllm-ascend
that referenced
this pull request
Jan 21, 2026
…r dsv32 (vllm-project#5958) ### What this PR does / why we need it? This PR is cherry-picked from vllm-project#5945. We leave only changes in platform.py. This PR aims to fix setting of `speculative_config.enforce_eager` in deepseek v3.2 mtp. The point is that, vllm sets `speculative_config.enforce_eager` as True if using deepseek_v32 with mtp. Since we support graph mode, we simply ignore it here. However, this fix will also implicitly ignore user setting of `speculative_config.enforce_eager`, we need to take care and remove it once vllm supports this feature. ### Does this PR introduce _any_ user-facing change? N/A ### How was this patch tested? by ci Signed-off-by: Zetong Li <slippersss@126.com> Signed-off-by: Mercykid-bash <ruanche0218@gmail.com>
starmountain1997
pushed a commit
to starmountain1997/vllm-ascend
that referenced
this pull request
Jan 31, 2026
…r dsv32 (vllm-project#5958) ### What this PR does / why we need it? This PR is cherry-picked from vllm-project#5945. We leave only changes in platform.py. This PR aims to fix setting of `speculative_config.enforce_eager` in deepseek v3.2 mtp. The point is that, vllm sets `speculative_config.enforce_eager` as True if using deepseek_v32 with mtp. Since we support graph mode, we simply ignore it here. However, this fix will also implicitly ignore user setting of `speculative_config.enforce_eager`, we need to take care and remove it once vllm supports this feature. ### Does this PR introduce _any_ user-facing change? N/A ### How was this patch tested? by ci Signed-off-by: Zetong Li <slippersss@126.com>
tangtiangu
pushed a commit
to tangtiangu/jiusi-vllm-ascend
that referenced
this pull request
Feb 24, 2026
…r dsv32 (vllm-project#5958) ### What this PR does / why we need it? This PR is cherry-picked from vllm-project#5945. We leave only changes in platform.py. This PR aims to fix setting of `speculative_config.enforce_eager` in deepseek v3.2 mtp. The point is that, vllm sets `speculative_config.enforce_eager` as True if using deepseek_v32 with mtp. Since we support graph mode, we simply ignore it here. However, this fix will also implicitly ignore user setting of `speculative_config.enforce_eager`, we need to take care and remove it once vllm supports this feature. ### Does this PR introduce _any_ user-facing change? N/A ### How was this patch tested? by ci Signed-off-by: Zetong Li <slippersss@126.com>
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
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.
What this PR does / why we need it?
This PR is cherry-picked from #5945. We leave only changes in platform.py.
This PR aims to fix setting of
speculative_config.enforce_eagerin deepseek v3.2 mtp. The point is that, vllm setsspeculative_config.enforce_eageras True if using deepseek_v32 with mtp. Since we support graph mode, we simply ignore it here. However, this fix will also implicitly ignore user setting ofspeculative_config.enforce_eager, we need to take care and remove it once vllm supports this feature.Does this PR introduce any user-facing change?
N/A
How was this patch tested?
by ci