[Bugfix] Fix the incorrect use of the output parameter in _forward_fia_slidingwindow#6469
[Bugfix] Fix the incorrect use of the output parameter in _forward_fia_slidingwindow#6469weijinqian0 merged 2 commits intovllm-project:mainfrom
Conversation
|
👋 Hi! Thank you for contributing to the vLLM Ascend project. The following points will speed up your PR merge:
If CI fails, you can run linting and testing checks locally according Contributing and Testing. |
Summary of ChangesHello @acat-rw, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request resolves a bug in the Highlights
🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console. Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request provides a good fix for the incorrect handling of the output parameter in the _forward_fia_slidingwindow function. The change correctly ensures that the output tensor is updated in-place, which aligns with its role as an output parameter.
To align with the repository's style guide, I suggest updating the pull request title. The pull request summary is well-written and follows the prescribed format.
Suggested PR Title:
[Attention][BugFix] Fix incorrect use of output parameter in _forward_fia_slidingwindowSuggested PR Summary:
### What this PR does / why we need it?
Fix the incorrect use of the `output` parameter in `_forward_fia_slidingwindow`:Original (incorrect)
output, _ = torch_npu.npu_fused_infer_attention_score(...)
output= output.view(batch_size, self.num_heads, self.head_size)
In the original writing, the `output `parameter was directly assigned a new value, which is inconsistent with the interface definition, resulting in the inability to directly update `output `when calling externally.
attn_output, _ = torch_npu.npu_fused_infer_attention_score(...)
attn_output = attn_output.view(batch_size, self.num_heads, self.head_size)
output[:batch_size] = attn_output[:batch_size]
### Does this PR introduce _any_ user-facing change?
No change.
### How was this patch tested?
vLLM ascend version: v0.13.0rc1
- vLLM version: v0.14.1
- vLLM main: https://github.com/vllm-project/vllm/commit/dc917cceb877dfd13f98c538c4c96158047d98bd
…window Signed-off-by: acat-rw <892882856@qq.com>
weijinqian0
added
ready
…to qwen3next_rebase * 'main' of https://github.com/vllm-project/vllm-ascend: (59 commits) [Feat.]: 310p support MOE models (vllm-project#6530) [Doc] backport 0.13.0 release note (vllm-project#6584) [CI] Update UT CANN version to 8.5.0 for main branch (vllm-project#6564) [CI] Change A2 runner (vllm-project#6557) [Bugfix] Fix the incorrect use of the output parameter in _forward_fia_slidingwindow (vllm-project#6469) [main2main] upgrade vllm main 0202 (vllm-project#6560) [CI][npugraph_ex]Fix npugraph ex e2e test (vllm-project#6553) [Feature]KV pool supports sparse attention (vllm-project#6339) [bugfix]Fix accuracy issue in PCP/DCP with speculative decoding (vllm-project#6491) perf: adaptive block size selection in linear_persistent kernel (vllm-project#6537) [ModelRunner][Fix] Pads query_start_loc to satisfy FIA/TND constraint (vllm-project#6475) [Bugfix]Fix of Pooling Code and Update of Pooling Usage Guide (vllm-project#6126) [Fusion] Add rmsnorm dynamic quant fusion pass (vllm-project#6274) [Bugfix] Synchronize only the current stream to avoid device sync (vllm-project#6432) [CI] Add long and short prompt tests for DeepSeek-V3.2 (vllm-project#6499) [Refactor] MLP weight prefetch to consistency with MoE Model's prefetching in terms of code and usage (vllm-project#6442) [bugfix][npugraph_ex]duplicate pattern issue (vllm-project#6513) [bugfix][npugraph_ex]add the extra check for allreduce rmsnorm fusion pass (vllm-project#6430) [Quant] GLM4.7-Flash Support W8A8 (vllm-project#6492) [Nightly][BugFix] Remove kv_cache nz test case for test_mla_preprocess_nq.py (vllm-project#6505) ...
…a_slidingwindow (vllm-project#6469) ### What this PR does / why we need it? Fix the incorrect use of the `output` parameter in `_forward_fia_slidingwindow`: ``` # Original (incorrect) output, _ = torch_npu.npu_fused_infer_attention_score(...) output= output.view(batch_size, self.num_heads, self.head_size) ``` In the original writing, the `output `parameter was directly assigned a new value, which is inconsistent with the interface definition, resulting in the inability to directly update `output `when calling externally. ``` attn_output, _ = torch_npu.npu_fused_infer_attention_score(...) attn_output = attn_output.view(batch_size, self.num_heads, self.head_size) output[:batch_size] = attn_output[:batch_size] ``` ### Does this PR introduce _any_ user-facing change? No change. Co-authored-by: GoCHug<gch59135228@163.com> ### How was this patch tested? vLLM ascend version: v0.13.0rc1 Signed-off-by: acat-rw <892882856@qq.com> Signed-off-by: momochenchuw <chenchuw@huawei.com>
…a_slidingwindow (vllm-project#6469) ### What this PR does / why we need it? Fix the incorrect use of the `output` parameter in `_forward_fia_slidingwindow`: ``` # Original (incorrect) output, _ = torch_npu.npu_fused_infer_attention_score(...) output= output.view(batch_size, self.num_heads, self.head_size) ``` In the original writing, the `output `parameter was directly assigned a new value, which is inconsistent with the interface definition, resulting in the inability to directly update `output `when calling externally. ``` attn_output, _ = torch_npu.npu_fused_infer_attention_score(...) attn_output = attn_output.view(batch_size, self.num_heads, self.head_size) output[:batch_size] = attn_output[:batch_size] ``` ### Does this PR introduce _any_ user-facing change? No change. Co-authored-by: GoCHug<gch59135228@163.com> ### How was this patch tested? vLLM ascend version: v0.13.0rc1 Signed-off-by: acat-rw <892882856@qq.com> Signed-off-by: zrj026 <zhangrunjiang026@gmail.com>
…a_slidingwindow (vllm-project#6469) ### What this PR does / why we need it? Fix the incorrect use of the `output` parameter in `_forward_fia_slidingwindow`: ``` # Original (incorrect) output, _ = torch_npu.npu_fused_infer_attention_score(...) output= output.view(batch_size, self.num_heads, self.head_size) ``` In the original writing, the `output `parameter was directly assigned a new value, which is inconsistent with the interface definition, resulting in the inability to directly update `output `when calling externally. ``` attn_output, _ = torch_npu.npu_fused_infer_attention_score(...) attn_output = attn_output.view(batch_size, self.num_heads, self.head_size) output[:batch_size] = attn_output[:batch_size] ``` ### Does this PR introduce _any_ user-facing change? No change. Co-authored-by: GoCHug<gch59135228@163.com> ### How was this patch tested? vLLM ascend version: v0.13.0rc1 Signed-off-by: acat-rw <892882856@qq.com>
…a_slidingwindow (vllm-project#6469) ### What this PR does / why we need it? Fix the incorrect use of the `output` parameter in `_forward_fia_slidingwindow`: ``` # Original (incorrect) output, _ = torch_npu.npu_fused_infer_attention_score(...) output= output.view(batch_size, self.num_heads, self.head_size) ``` In the original writing, the `output `parameter was directly assigned a new value, which is inconsistent with the interface definition, resulting in the inability to directly update `output `when calling externally. ``` attn_output, _ = torch_npu.npu_fused_infer_attention_score(...) attn_output = attn_output.view(batch_size, self.num_heads, self.head_size) output[:batch_size] = attn_output[:batch_size] ``` ### Does this PR introduce _any_ user-facing change? No change. Co-authored-by: GoCHug<gch59135228@163.com> ### How was this patch tested? vLLM ascend version: v0.13.0rc1 Signed-off-by: acat-rw <892882856@qq.com> Signed-off-by: zrj026 <zhangrunjiang026@gmail.com>
…a_slidingwindow (vllm-project#6469) ### What this PR does / why we need it? Fix the incorrect use of the `output` parameter in `_forward_fia_slidingwindow`: ``` # Original (incorrect) output, _ = torch_npu.npu_fused_infer_attention_score(...) output= output.view(batch_size, self.num_heads, self.head_size) ``` In the original writing, the `output `parameter was directly assigned a new value, which is inconsistent with the interface definition, resulting in the inability to directly update `output `when calling externally. ``` attn_output, _ = torch_npu.npu_fused_infer_attention_score(...) attn_output = attn_output.view(batch_size, self.num_heads, self.head_size) output[:batch_size] = attn_output[:batch_size] ``` ### Does this PR introduce _any_ user-facing change? No change. Co-authored-by: GoCHug<gch59135228@163.com> ### How was this patch tested? vLLM ascend version: v0.13.0rc1 Signed-off-by: acat-rw <892882856@qq.com>
3 participants
What this PR does / why we need it?
Fix the incorrect use of the
outputparameter in_forward_fia_slidingwindow:In the original writing, the
outputparameter was directly assigned a new value, which is inconsistent with the interface definition, resulting in the inability to directly updateoutputwhen calling externally.Does this PR introduce any user-facing change?
No change.
Co-authored-by: GoCHuggch59135228@163.com
How was this patch tested?
vLLM ascend version: v0.13.0rc1