Closed
Conversation
Signed-off-by: ttanzhiqiang <389825161@qq.com>
ttanzhiqiang
force-pushed
the
group_gemm_nz
branch
from
6f37250 to
52d067d
Compare
wangxiyuan
approved these changes
May 22, 2025
Collaborator
wangxiyuan
left a comment
wangxiyuan
left a comment
There was a problem hiding this comment.
not sure if this change conflict with #907 but LGTM at least.
| layer.w2_weight.data = layer.w2_weight.data.transpose( | ||
| 1, 2).contiguous() | ||
| torch_npu.npu_format_cast_(layer.w13_weight, 29) | ||
| torch_npu.npu_format_cast_(layer.w2_weight, 29) |
Collaborator
There was a problem hiding this comment.
Thanks for contribution. The transformation of grouped_matmul may lead to accuracy problem until newer torch_npu releases. I think it is good to hang up this PR temporarily.
76 tasks
Merged
Collaborator
|
this can not be merged until new version of torch_npu for community |
wangxiyuan
pushed a commit
that referenced
this pull request
Jun 11, 2025
### What this PR does / why we need it? Single machine 16 cards deepseekr1 attention (tp8/dp2) / moe(etp) Best performance rely on: vllm-ascend commit id:da9acfca6053352730fce75fb772e214755d0341 vllm commit id:b124e1085b1bf977e3dac96d99ffd9d8ddfdb6cc + #910 + [Reduce _npu_flash_attention mask to 128x128 for memory savings] #1100 [Reduce memory usage by splitting tokens in fused_experts] --------- Signed-off-by: ttanzhiqiang <389825161@qq.com>
momo609
pushed a commit
to momo609/vllm-ascend
that referenced
this pull request
Jun 17, 2025
### What this PR does / why we need it? Single machine 16 cards deepseekr1 attention (tp8/dp2) / moe(etp) Best performance rely on: vllm-ascend commit id:da9acfca6053352730fce75fb772e214755d0341 vllm commit id:b124e1085b1bf977e3dac96d99ffd9d8ddfdb6cc + vllm-project#910 + [Reduce _npu_flash_attention mask to 128x128 for memory savings] vllm-project#1100 [Reduce memory usage by splitting tokens in fused_experts] --------- Signed-off-by: ttanzhiqiang <389825161@qq.com>
momo609
pushed a commit
to momo609/vllm-ascend
that referenced
this pull request
Jun 17, 2025
### What this PR does / why we need it? Single machine 16 cards deepseekr1 attention (tp8/dp2) / moe(etp) Best performance rely on: vllm-ascend commit id:da9acfca6053352730fce75fb772e214755d0341 vllm commit id:b124e1085b1bf977e3dac96d99ffd9d8ddfdb6cc + vllm-project#910 + [Reduce _npu_flash_attention mask to 128x128 for memory savings] vllm-project#1100 [Reduce memory usage by splitting tokens in fused_experts] --------- Signed-off-by: ttanzhiqiang <389825161@qq.com> Signed-off-by: wangxiaoxin (A) <wangxiaoxin7@huawei.com>
momo609
pushed a commit
to momo609/vllm-ascend
that referenced
this pull request
Jun 17, 2025
### What this PR does / why we need it? Single machine 16 cards deepseekr1 attention (tp8/dp2) / moe(etp) Best performance rely on: vllm-ascend commit id:da9acfca6053352730fce75fb772e214755d0341 vllm commit id:b124e1085b1bf977e3dac96d99ffd9d8ddfdb6cc + vllm-project#910 + [Reduce _npu_flash_attention mask to 128x128 for memory savings] vllm-project#1100 [Reduce memory usage by splitting tokens in fused_experts] --------- Signed-off-by: ttanzhiqiang <389825161@qq.com> Signed-off-by: wangxiaoxin (A) <wangxiaoxin7@huawei.com>
Contributor
|
This pull request has conflicts, please resolve those before we can evaluate the pull request. |
Codecov Report❌ Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #910 +/- ##
==========================================
- Coverage 27.39% 27.24% -0.16%
==========================================
Files 56 56
Lines 6191 6222 +31
==========================================
- Hits 1696 1695 -1
- Misses 4495 4527 +32
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
shiyuan680
pushed a commit
to raindaywhu/vllm-ascend
that referenced
this pull request
Jul 7, 2025
### What this PR does / why we need it? Single machine 16 cards deepseekr1 attention (tp8/dp2) / moe(etp) Best performance rely on: vllm-ascend commit id:da9acfca6053352730fce75fb772e214755d0341 vllm commit id:b124e1085b1bf977e3dac96d99ffd9d8ddfdb6cc + vllm-project#910 + [Reduce _npu_flash_attention mask to 128x128 for memory savings] vllm-project#1100 [Reduce memory usage by splitting tokens in fused_experts] --------- Signed-off-by: ttanzhiqiang <389825161@qq.com>
Contributor
|
This pull request has conflicts, please resolve those before we can evaluate the pull request. |
chopper0126
pushed a commit
to chopper0126/vllm-ascend
that referenced
this pull request
Oct 16, 2025
### What this PR does / why we need it? Single machine 16 cards deepseekr1 attention (tp8/dp2) / moe(etp) Best performance rely on: vllm-ascend commit id:da9acfca6053352730fce75fb772e214755d0341 vllm commit id:b124e1085b1bf977e3dac96d99ffd9d8ddfdb6cc + vllm-project#910 + [Reduce _npu_flash_attention mask to 128x128 for memory savings] vllm-project#1100 [Reduce memory usage by splitting tokens in fused_experts] --------- Signed-off-by: ttanzhiqiang <389825161@qq.com>
Angazenn
pushed a commit
to Angazenn/vllm-ascend
that referenced
this pull request
Oct 21, 2025
### What this PR does / why we need it? Single machine 16 cards deepseekr1 attention (tp8/dp2) / moe(etp) Best performance rely on: vllm-ascend commit id:da9acfca6053352730fce75fb772e214755d0341 vllm commit id:b124e1085b1bf977e3dac96d99ffd9d8ddfdb6cc + vllm-project#910 + [Reduce _npu_flash_attention mask to 128x128 for memory savings] vllm-project#1100 [Reduce memory usage by splitting tokens in fused_experts] --------- Signed-off-by: ttanzhiqiang <389825161@qq.com>
Collaborator
|
i thinks this one can be closed now. Feel free to create a new one if it's still needed. |
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
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?
Update weight format to improve TPOP 3ms performance
Insert code to convert weight format of specific layers Need to update group gemm TASK_QUEUE_ENABLE=1 and TASK_QUEUE_ENABLE=2 of torch_npu
Does this PR introduce any user-facing change?
How was this patch tested?