Skip to content

[CI]update triton ascend version#5392

Merged
MengqingCao merged 10 commits intovllm-project:mainfrom
Meihan-chen:triton_ut
Dec 30, 2025
Merged

[CI]update triton ascend version#5392
MengqingCao merged 10 commits intovllm-project:mainfrom
Meihan-chen:triton_ut

Conversation

@Meihan-chen
Copy link
Copy Markdown
Contributor

@Meihan-chen Meihan-chen commented Dec 26, 2025 •
edited
Loading

What this PR does / why we need it?

update triton-ascend version to 1229 and bisheng version in 1225;

Does this PR introduce any user-facing change?

How was this patch tested?

@gemini-code-assist
Copy link
Copy Markdown
Contributor

gemini-code-assist bot commented Dec 26, 2025

Note

Gemini is unable to generate a review for this pull request due to the file types involved not being currently supported.

@wxsIcey wxsIcey added ready read for review ready-for-test start test by label for PR labels Dec 26, 2025
@github-actions
Copy link
Copy Markdown
Contributor

github-actions bot commented Dec 26, 2025

👋 Hi! Thank you for contributing to the vLLM Ascend project. The following points will speed up your PR merge:‌‌

  • A PR should do only one thing, smaller PRs enable faster reviews.
  • Every PR should include unit tests and end-to-end tests ‌to ensure it works and is not broken by other future PRs.
  • Write the commit message by fulfilling the PR description to help reviewer and future developers understand.

If CI fails, you can run linting and testing checks locally according Contributing and Testing.

@Meihan-chen
Copy link
Copy Markdown
Contributor Author

Meihan-chen commented Dec 27, 2025

All check have passed in commit 88f1e5c, https://github.com/vllm-project/vllm-ascend/actions/runs/20524563067/job/58965516202
https://github.com/vllm-project/vllm-ascend/actions/runs/20524563056/job/58965789512

@Meihan-chen
update triton ascend version
8de985b 
Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>
@Meihan-chen
update bisheng version
ca579ee 
Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>
@Meihan-chen
update triton version
df6a7c1 
Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>
@Meihan-chen
update nightly triton
cc829fa 
Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>
@Meihan-chen
fix test_camem failed with triton
d915195 
Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>
@Meihan-chen Meihan-chen force-pushed the triton_ut branch 3 times, most recently from 91e794b to 4a5e98d Compare December 29, 2025 06:15
@Meihan-chen
update triton ver to 1229 and fix test_aclgraph_mem failed with triton
9d6e913 
Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>
@Meihan-chen
update Bisheng ver
a9927f6 
Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>
@github-actions
Copy link
Copy Markdown
Contributor

github-actions bot commented Dec 29, 2025

This pull request has conflicts, please resolve those before we can evaluate the pull request.

whx-sjtu
whx-sjtu requested changes Dec 29, 2025
View reviewed changes
Comment thread vllm_ascend/sample/rejection_sampler.py Outdated
n = cu_num_draft_tokens.numel()
BLOCK_SIZE = 2
grid = triton.cdiv(n, BLOCK_SIZE)
from triton.runtime import driver # type: ignore
Copy link
Copy Markdown
Collaborator

@whx-sjtu whx-sjtu Dec 29, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

reuse get_vectorcore_num() in

vllm-ascend/vllm_ascend/ops/triton/triton_utils.py

Line 27 in 92353c0

def get_vectorcore_num():

Copy link
Copy Markdown
Contributor Author

@Meihan-chen Meihan-chen Dec 29, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks, I will update this in a new PR to fix the Triton test file bug.

@Meihan-chen
update triton url and doc
dc8dab1 
Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>
@MengqingCao
Copy link
Copy Markdown
Collaborator

MengqingCao commented Dec 30, 2025

all ci passed in https://github.com/vllm-project/vllm-ascend/actions/runs/20569909712/job/59083393674?pr=5392

MengqingCao
MengqingCao reviewed Dec 30, 2025
View reviewed changes
Comment thread docs/source/tutorials/DeepSeek-V3.2.md Outdated

```bash
source /usr/local/Ascend/ascend-toolkit/8.3.RC2/bisheng_toolkit/set_env.sh
BISHENG_NAME="Ascend-BiSheng-toolkit_aarch64_20251225.run"
Copy link
Copy Markdown
Collaborator

@MengqingCao MengqingCao Dec 30, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

plz use uname -i to get the architecture dynamicly, thus we could satisfy the x86 users also

Copy link
Copy Markdown
Contributor Author

@Meihan-chen Meihan-chen Dec 30, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

thanks, it has been update in $(uname -i)

@Meihan-chen
Copy link
Copy Markdown
Contributor Author

Meihan-chen commented Dec 30, 2025

All check have passed in commit dc8dab1 https://github.com/vllm-project/vllm-ascend/actions/runs/20569909713/job/59077023380 https://github.com/vllm-project/vllm-ascend/actions/runs/20569909712/job/59083393674

@Meihan-chen
update doc use uname -i
e56f1ab 
Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>
MengqingCao
MengqingCao approved these changes Dec 30, 2025
View reviewed changes
Copy link
Copy Markdown
Collaborator

@MengqingCao MengqingCao left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM, thx for this!

@MengqingCao MengqingCao merged commit 8c4e9bb into vllm-project:main Dec 30, 2025
4 of 6 checks passed
845473182 pushed a commit to 845473182/vllm-ascend that referenced this pull request Dec 31, 2025
Merge branch 'main' of https://github.com/vllm-project/vllm-ascend in…
048b04f 
…to FIA_rebase

* 'main' of https://github.com/vllm-project/vllm-ascend: (88 commits)
  [1/N] Refactor nightly test structure (vllm-project#5479)
  Docs: Remove deprecated --task parameter for embedding models (vllm-project#5257)
  Revert "moe_gating_top_k" (vllm-project#5512)
  [Doc] Fix issue link for 0.12.0 (vllm-project#5500)
  [CI]update triton ascend version (vllm-project#5392)
  moe_gating_top_k (vllm-project#5271)
  [refactor] refactor model runner capture model (vllm-project#5230)
  Update corresponding vllm commit ID to 12 29 (vllm-project#5475)
  [Kernel]update csrc cmakelist for open-source cann (vllm-project#5458)
  [OP] add custom op aclnnMoeInitRoutingCustom (vllm-project#5251)
  [Refactor][EAGLE] 1/N delete __init__ in mtp_proposer (vllm-project#5176)
  [Refactor][Triton] Move reject sample triton kernels into ops/triton (vllm-project#5324)
  [Feature] support eager mode in model runner v2 (vllm-project#5210)
  [feature] fia support sliding windows (vllm-project#5239)
  Optimize some rejectsampler functions to make npu op launch non-blocking (vllm-project#4587)
  [Feature] Support to use fullgraph with eagle (vllm-project#5118)
  [EPLB][refactor] Modification of the initialization logic for expert_map and log2phy（depend on pr5285） (vllm-project#5311)
  [Refactor]6/N Extract common code of class AscendMLAImpl (vllm-project#5314)
  [Refactor] cache cos/sin in mla & remove parameter model in builder. (vllm-project#5277)
  update vllm pin to 12.27 (vllm-project#5412)
  ...
shenchuxiaofugui pushed a commit to shenchuxiaofugui/vllm-ascend that referenced this pull request Dec 31, 2025
@Meihan-chen @shenchuxiaofugui
[CI]update triton ascend version (vllm-project#5392)
ec173d2 
### What this PR does / why we need it?
update triton-ascend version to 1229 and bisheng version in 1225;

- vLLM version: release/v0.13.0
- vLLM main:
vllm-project/vllm@254f6b9
---------
Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>
ZRJ026 pushed a commit to ZRJ026/vllm-ascend that referenced this pull request Feb 28, 2026
@Meihan-chen
[CI]update triton ascend version (vllm-project#5392)
93b59c7 
### What this PR does / why we need it?
update triton-ascend version to 1229 and bisheng version in 1225;

- vLLM version: release/v0.13.0
- vLLM main:
vllm-project/vllm@254f6b9
---------
Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>
Signed-off-by: zrj026 <zhangrunjiang026@gmail.com>
maoxx241 pushed a commit to maoxx241/vllm-ascend that referenced this pull request Mar 2, 2026
@Meihan-chen @maoxx241
[CI]update triton ascend version (vllm-project#5392)
17e8670 
### What this PR does / why we need it?
update triton-ascend version to 1229 and bisheng version in 1225;

- vLLM version: release/v0.13.0
- vLLM main:
vllm-project/vllm@254f6b9
---------
Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>
ZRJ026 pushed a commit to ZRJ026/vllm-ascend that referenced this pull request Mar 4, 2026
@Meihan-chen
[CI]update triton ascend version (vllm-project#5392)
2247bcb 
### What this PR does / why we need it?
update triton-ascend version to 1229 and bisheng version in 1225;

- vLLM version: release/v0.13.0
- vLLM main:
vllm-project/vllm@254f6b9
---------
Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>
Signed-off-by: zrj026 <zhangrunjiang026@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@whx-sjtu whx-sjtu whx-sjtu requested changes

@MengqingCao MengqingCao MengqingCao approved these changes

Assignees

No one assigned

Labels

ci/build ready read for review ready-for-test start test by label for PR

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

4 participants

@Meihan-chen @MengqingCao @whx-sjtu @wxsIcey