add optimze of dsv3 #970
Open
add optimze of dsv3 #970
+257
−3
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
MengqingCao
reviewed
May 29, 2025
momo609
force-pushed
the
main
branch
3 times, most recently
from
52aff53 to
c35b678
Compare
wangxiyuan
reviewed
May 30, 2025
wangxiyuan
reviewed
May 30, 2025
momo609
force-pushed
the
main
branch
3 times, most recently
from
efe0a26 to
90ae7ec
Compare
Signed-off-by: wangxiaoxin (A) <w00664509@china.huawei.com>
| @@ -225,8 +225,7 @@ def forward(self, hidden_states: torch.Tensor) -> torch.Tensor: | |||
| enable_force_load_balance = False | |||
| num_tokens, hidden_dim = hidden_states.shape | |||
|
|
|||
| if self.n_shared_experts is not None: | |||
| shared_output = self.shared_experts(hidden_states) | |||
| old_hidden_states = hidden_states.detach() | |||
There was a problem hiding this comment.
Can you upload the performance profiling on this part? Distach this variable from the pytorch graph seems can't actually triggers the parallel execution according to my knowledge.
Yikun
reviewed
May 30, 2025
| _info "====> Start simple_test" | ||
| simple_test | ||
| _info "====> Start quickstart_offline_test" | ||
| quickstart_offline_test | ||
| _info "====> Start quickstart_online_test" | ||
| quickstart_online_test | ||
| _info "====> Start quickstart_offline_test_topk" |
There was a problem hiding this comment.
We should add offline test in py by setting os.eviron rather than here:
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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?
Optimize the performance of calculation logic in sampler and deepseekv2.
Does this PR introduce any user-facing change?
Added VLLM_ENABLE_TOPK_OPTIMZE config in sampler
How was this patch tested?
pytest test_sampler.py