[Build][0.7.3] Integrate MindIE Turbo into vLLM Ascend #708
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
github-actions
bot
added
the
documentation
MengqingCao
commented
Apr 28, 2025
MengqingCao
changed the title
46 tasks
Yikun
reviewed
May 1, 2025
docs/source/installation.md
Outdated
| wget https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/CANN/CANN%208.0.0/Ascend-cann-toolkit_8.0.0_linux-aarch64.run | ||
| chmod +x ./Ascend-cann-toolkit_8.0.0_linux-aarch64.run | ||
| ./Ascend-cann-toolkit_8.0.0_linux-aarch64.run --full | ||
| wget https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/CANN/CANN%208.1.RC1/Ascend-cann-toolkit_8.1.RC1_linux-"$(uname -i)".run |
There was a problem hiding this comment.
This guide takes aarch64 as an example. If you run on x86, you need to replace
aarch64withx86_64for the package name shown below.
The note can be removed
docs/source/installation.md
Outdated
| ```{code-block} bash | ||
| :substitutions: | ||
|
|
||
| pip install mindie_turbo==|pip_vllm_ascend_version| |
There was a problem hiding this comment.
this should be pip_mindie_turbo_version
Yikun
force-pushed
the
turbo
branch
2 times, most recently
from
4748a26 to
8ffa764
Compare
|
The ascend ci failed due to pull image time out, already synced this info to infra team |
Yikun
force-pushed
the
turbo
branch
3 times, most recently
from
84d352b to
7406af5
Compare
|
Looks ready, the only thing we need to do is make sure mindie turbo integration doc works, wait mindie turbo release. Let's extract a new PR to upgrade the 8.1rc1 first: #746 |
Yikun
added a commit
that referenced
this pull request
May 5, 2025
### What this PR does / why we need it? Make CANN version bump separately from #708 - Upgrade CANN version to 8.1.rc1 - Add prefix to speed up download `m.daocloud.io/quay.io/ascend/cann:8.1.rc1-910b-ubuntu22.04-py3.10` - Address tail sapce for Dockerfile.openEuler - Add note for `/workspace` and `/vllm-workspace` as followup of #741 ### Does this PR introduce _any_ user-facing change? no ### How was this patch tested? CI passed Co-authored-by: MengqingCao <[email protected]> Signed-off-by: Yikun Jiang <[email protected]> Co-authored-by: MengqingCao <[email protected]>
Co-authored-by: Yikun Jiang <[email protected]> Signed-off-by: MengqingCao <[email protected]>
wangxiyuan
approved these changes
May 7, 2025
Yikun
reviewed
May 8, 2025
Yikun
reviewed
May 8, 2025
Yikun
changed the title
Yikun
force-pushed
the
turbo
branch
2 times, most recently
from
a57f7e7 to
e012433
Compare
Signed-off-by: MengqingCao <[email protected]> Signed-off-by: Yikun Jiang <[email protected]>
hfadzxy
pushed a commit
to hfadzxy/vllm-ascend
that referenced
this pull request
May 8, 2025
) Integrate MindIE Turbo into vLLM Ascend: - Added support for MindIE Turbo in `setup.py` via an optional dependency under `extras_require`. - Enhanced `try_register_lib` utility to log specific exceptions when MindIE Turbo is not found. - Updated documentation to include instructions for installing MindIE Turbo: - Improved documentation with links to Bisheng compiler optimization tutorials and MindIE Turbo documentation. NO CI passed --------- Signed-off-by: MengqingCao <[email protected]> Signed-off-by: Yikun Jiang <[email protected]> Signed-off-by: hfadzxy <[email protected]>
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?
Integrate MindIE Turbo into vLLM Ascend:
setup.pyvia an optional dependency underextras_require.try_register_libutility to log specific exceptions when MindIE Turbo is not found.Does this PR introduce any user-facing change?
NO
How was this patch tested?
CI passed