[Feature] Implement EP-compatible fused_moe #121
Merged
+366
−129
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
yiz-liu
changed the title
yiz-liu
changed the title
yiz-liu
force-pushed
the
main
branch
3 times, most recently
from
67429eb to
b8d514d
Compare
wuhuikx
approved these changes
Mar 8, 2025
ganyi1996ppo
reviewed
Mar 9, 2025
ganyi1996ppo
approved these changes
Mar 10, 2025
added 7 commits
March 11, 2025 10:10
Signed-off-by: Yizhou Liu <liuyizhou5@h-partners.com>
Signed-off-by: Yizhou Liu <liuyizhou5@h-partners.com>
Signed-off-by: Yizhou Liu <liuyizhou5@h-partners.com>
Signed-off-by: Yizhou Liu <liuyizhou5@h-partners.com>
Signed-off-by: Yizhou Liu <liuyizhou5@h-partners.com>
Signed-off-by: Yizhou Liu <liuyizhou5@h-partners.com>
Co-authored-by: Yaphets24 d_mym0618@163.com Signed-off-by: Yizhou Liu <liuyizhou5@h-partners.com>
yiz-liu
force-pushed
the
main
branch
2 times, most recently
from
c6117aa to
5768e51
Compare
Co-authored-by: Yaphets24 d_mym0618@163.com Signed-off-by: Yizhou Liu <liuyizhou5@h-partners.com>
yiz-liu
changed the title
wangxiyuan
approved these changes
Mar 11, 2025
Angazenn
pushed a commit
to Angazenn/vllm-ascend
that referenced
this pull request
Mar 18, 2025
### What this PR does / why we need it?
Enable Expert-Parallel for ascend devices.
### Does this PR introduce _any_ user-facing change?
Enable EP
add `enable_expert_parallel=True` in your offline inference scripts,
like this:
```python
llm = LLM(
model="/path/to/model",
trust_remote_code=True,
tensor_parallel_size=4,
max_model_len=4096,
enforce_eager=True,
distributed_executor_backend="mp",
enable_expert_parallel=True,
)
```
### How was this patch tested?
Please use the `main` branch of vLLM.
---------
Signed-off-by: Yizhou Liu <liuyizhou5@h-partners.com>
Co-authored-by: Yizhou Liu <liuyizhou5@h-partners.com>
Signed-off-by: angazenn <zengyanjia@huawei.com>
ttanzhiqiang
pushed a commit
to ttanzhiqiang/vllm-ascend
that referenced
this pull request
Apr 27, 2025
### What this PR does / why we need it?
Enable Expert-Parallel for ascend devices.
### Does this PR introduce _any_ user-facing change?
Enable EP
add `enable_expert_parallel=True` in your offline inference scripts,
like this:
```python
llm = LLM(
model="/path/to/model",
trust_remote_code=True,
tensor_parallel_size=4,
max_model_len=4096,
enforce_eager=True,
distributed_executor_backend="mp",
enable_expert_parallel=True,
)
```
### How was this patch tested?
Please use the `main` branch of vLLM.
---------
Signed-off-by: Yizhou Liu <liuyizhou5@h-partners.com>
Co-authored-by: Yizhou Liu <liuyizhou5@h-partners.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?
Enable Expert-Parallel for ascend devices.
### Does this PR introduce _any_ user-facing change?
Enable EP
add `enable_expert_parallel=True` in your offline inference scripts,
like this:
```python
llm = LLM(
model="/path/to/model",
trust_remote_code=True,
tensor_parallel_size=4,
max_model_len=4096,
enforce_eager=True,
distributed_executor_backend="mp",
enable_expert_parallel=True,
)
```
### How was this patch tested?
Please use the `main` branch of vLLM.
---------
Signed-off-by: Yizhou Liu <liuyizhou5@h-partners.com>
Co-authored-by: Yizhou Liu <liuyizhou5@h-partners.com>
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?
Enable Expert-Parallel for ascend devices.
Does this PR introduce any user-facing change?
Enable EP
add
enable_expert_parallel=Truein your offline inference scripts, like this:How was this patch tested?
Please use the
mainbranch of vLLM.