[Refactor] Pre-transpose MoE weights for improved performance #2025
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: Yizhou Liu <liu_yizhou@outlook.com>
|
This pull request has conflicts, please resolve those before we can evaluate the pull request. |
Collaborator
|
please rebase to fix the merge conflict if this PR is still needed. |
Collaborator
Author
|
Implemented in #2614 . |
wangxiyuan
pushed a commit
that referenced
this pull request
Aug 30, 2025
… Graph (#2614) ### What this PR does / why we need it? * **Unify execution paths:** Consolidates the quantized and non-quantized execution paths into a single `fused_experts` function, removing duplicated logic and making the control flow clearer and easier to maintain. * **W8A8 dynamic quantization:** Adds support for W8A8 dynamic quantization inside the unified MoE kernel. Communication routines are updated to correctly handle dynamic quantization scales for activations. * **Weight pre-processing:** Prae-transpose the `w13` and `w2` weight matrices (as implemented in PR #2025) so that quantized and non-quantized models follow the same code path for the MoE gating, up-projection, and down-projection operations. * **All-to-all communication:** Adds an `all-to-all` collective communication pattern. For large token counts on modern hardware, `all-to-all` is more efficient than the previous `all-gather` strategy. However, `all-to-all` is not really captured and replayed due to multiple D2H operations which will trigger synchronization, and thus raise error when capture graphs. We only use `all-to-all` when fallback to `compiled_graph_for_general_shape`. * **Dynamic communication selection:** The model runner now selects the optimal MoE communication method (`mc2`, `allgather`, or `alltoall`) at runtime based on token count and the Ascend SoC version. * **Limitation:** `all-gather` is not yet supported for quantized models, which means there is still something left to do on A2. ### Does this PR introduce _any_ user-facing change? None. ### How was this patch tested? No further test cases needed. - vLLM version: v0.10.1.1 - vLLM main: vllm-project/vllm@d660c98 --------- Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
wenba0
pushed a commit
to wenba0/vllm-ascend
that referenced
this pull request
Sep 5, 2025
… Graph (vllm-project#2614) ### What this PR does / why we need it? * **Unify execution paths:** Consolidates the quantized and non-quantized execution paths into a single `fused_experts` function, removing duplicated logic and making the control flow clearer and easier to maintain. * **W8A8 dynamic quantization:** Adds support for W8A8 dynamic quantization inside the unified MoE kernel. Communication routines are updated to correctly handle dynamic quantization scales for activations. * **Weight pre-processing:** Prae-transpose the `w13` and `w2` weight matrices (as implemented in PR vllm-project#2025) so that quantized and non-quantized models follow the same code path for the MoE gating, up-projection, and down-projection operations. * **All-to-all communication:** Adds an `all-to-all` collective communication pattern. For large token counts on modern hardware, `all-to-all` is more efficient than the previous `all-gather` strategy. However, `all-to-all` is not really captured and replayed due to multiple D2H operations which will trigger synchronization, and thus raise error when capture graphs. We only use `all-to-all` when fallback to `compiled_graph_for_general_shape`. * **Dynamic communication selection:** The model runner now selects the optimal MoE communication method (`mc2`, `allgather`, or `alltoall`) at runtime based on token count and the Ascend SoC version. * **Limitation:** `all-gather` is not yet supported for quantized models, which means there is still something left to do on A2. ### Does this PR introduce _any_ user-facing change? None. ### How was this patch tested? No further test cases needed. - vLLM version: v0.10.1.1 - vLLM main: vllm-project/vllm@d660c98 --------- Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com> Signed-off-by: lijiaojiao <lijiaojiao990304@163.com>
wangxiaoteng888
pushed a commit
to LCAIZJ/vllm-ascend
that referenced
this pull request
Sep 25, 2025
… Graph (vllm-project#2614) ### What this PR does / why we need it? * **Unify execution paths:** Consolidates the quantized and non-quantized execution paths into a single `fused_experts` function, removing duplicated logic and making the control flow clearer and easier to maintain. * **W8A8 dynamic quantization:** Adds support for W8A8 dynamic quantization inside the unified MoE kernel. Communication routines are updated to correctly handle dynamic quantization scales for activations. * **Weight pre-processing:** Prae-transpose the `w13` and `w2` weight matrices (as implemented in PR vllm-project#2025) so that quantized and non-quantized models follow the same code path for the MoE gating, up-projection, and down-projection operations. * **All-to-all communication:** Adds an `all-to-all` collective communication pattern. For large token counts on modern hardware, `all-to-all` is more efficient than the previous `all-gather` strategy. However, `all-to-all` is not really captured and replayed due to multiple D2H operations which will trigger synchronization, and thus raise error when capture graphs. We only use `all-to-all` when fallback to `compiled_graph_for_general_shape`. * **Dynamic communication selection:** The model runner now selects the optimal MoE communication method (`mc2`, `allgather`, or `alltoall`) at runtime based on token count and the Ascend SoC version. * **Limitation:** `all-gather` is not yet supported for quantized models, which means there is still something left to do on A2. ### Does this PR introduce _any_ user-facing change? None. ### How was this patch tested? No further test cases needed. - vLLM version: v0.10.1.1 - vLLM main: vllm-project/vllm@d660c98 --------- Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
chopper0126
pushed a commit
to chopper0126/vllm-ascend
that referenced
this pull request
Sep 26, 2025
… Graph (vllm-project#2614) ### What this PR does / why we need it? * **Unify execution paths:** Consolidates the quantized and non-quantized execution paths into a single `fused_experts` function, removing duplicated logic and making the control flow clearer and easier to maintain. * **W8A8 dynamic quantization:** Adds support for W8A8 dynamic quantization inside the unified MoE kernel. Communication routines are updated to correctly handle dynamic quantization scales for activations. * **Weight pre-processing:** Prae-transpose the `w13` and `w2` weight matrices (as implemented in PR vllm-project#2025) so that quantized and non-quantized models follow the same code path for the MoE gating, up-projection, and down-projection operations. * **All-to-all communication:** Adds an `all-to-all` collective communication pattern. For large token counts on modern hardware, `all-to-all` is more efficient than the previous `all-gather` strategy. However, `all-to-all` is not really captured and replayed due to multiple D2H operations which will trigger synchronization, and thus raise error when capture graphs. We only use `all-to-all` when fallback to `compiled_graph_for_general_shape`. * **Dynamic communication selection:** The model runner now selects the optimal MoE communication method (`mc2`, `allgather`, or `alltoall`) at runtime based on token count and the Ascend SoC version. * **Limitation:** `all-gather` is not yet supported for quantized models, which means there is still something left to do on A2. ### Does this PR introduce _any_ user-facing change? None. ### How was this patch tested? No further test cases needed. - vLLM version: v0.10.1.1 - vLLM main: vllm-project/vllm@d660c98 --------- Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
Angazenn
pushed a commit
to Angazenn/vllm-ascend
that referenced
this pull request
Oct 21, 2025
… Graph (vllm-project#2614) ### What this PR does / why we need it? * **Unify execution paths:** Consolidates the quantized and non-quantized execution paths into a single `fused_experts` function, removing duplicated logic and making the control flow clearer and easier to maintain. * **W8A8 dynamic quantization:** Adds support for W8A8 dynamic quantization inside the unified MoE kernel. Communication routines are updated to correctly handle dynamic quantization scales for activations. * **Weight pre-processing:** Prae-transpose the `w13` and `w2` weight matrices (as implemented in PR vllm-project#2025) so that quantized and non-quantized models follow the same code path for the MoE gating, up-projection, and down-projection operations. * **All-to-all communication:** Adds an `all-to-all` collective communication pattern. For large token counts on modern hardware, `all-to-all` is more efficient than the previous `all-gather` strategy. However, `all-to-all` is not really captured and replayed due to multiple D2H operations which will trigger synchronization, and thus raise error when capture graphs. We only use `all-to-all` when fallback to `compiled_graph_for_general_shape`. * **Dynamic communication selection:** The model runner now selects the optimal MoE communication method (`mc2`, `allgather`, or `alltoall`) at runtime based on token count and the Ascend SoC version. * **Limitation:** `all-gather` is not yet supported for quantized models, which means there is still something left to do on A2. ### Does this PR introduce _any_ user-facing change? None. ### How was this patch tested? No further test cases needed. - vLLM version: v0.10.1.1 - vLLM main: vllm-project/vllm@d660c98 --------- Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
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?
Pre-transpose MoE weights for improved performance
Does this PR introduce any user-facing change?
None.
How was this patch tested?
No further test needed.