Skip to content

Upgrade to 0.11.1 newest vllm commit#3982

Merged
wangxiyuan merged 1 commit intovllm-project:mainfrom
22dimensions:update
Nov 12, 2025
Merged

Upgrade to 0.11.1 newest vllm commit#3982
wangxiyuan merged 1 commit intovllm-project:mainfrom
22dimensions:update

Conversation

@22dimensions
Copy link
Copy Markdown
Collaborator

@22dimensions 22dimensions commented Nov 4, 2025

What this PR does / why we need it?

adapt vllm-ascend main branch with vllm releases/v0.11.1

fix forward context not set in test_vlm.py caused by: vllm-project/vllm#23207

fix import cdiv round failed caused by: vllm-project/vllm#27188

fix import init_cached_hf_modules failed caused by: vllm-project/vllm#27567

adapt triton kernel fused_recurrent_gated_delta_rule_fwd_kernel caused by: vllm-project/vllm#27654

  • remove unused code in sigmoid_gating.py
    • class FusedRecurrentFunction , fused_recurrent_gated_delta_rule, fused_recurrent_gated_delta_rule_fwd

Does this PR introduce any user-facing change?

No

How was this patch tested?

CI

@github-actions
Copy link
Copy Markdown
Contributor

github-actions Bot commented Nov 4, 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.

Copy link
Copy Markdown
Contributor

@gemini-code-assist gemini-code-assist Bot left a comment

Choose a reason for hiding this comment

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

Code Review

This pull request aims to upgrade the vLLM dependency to version 0.11.1. The changes primarily involve adapting to new import paths in the upstream library. However, the implementation of the version checks is not robust, using exact version matching which can lead to import errors with other vLLM versions. I have provided critical feedback and suggestions to fix this issue across multiple files. The rest of the changes appear to be correct for this upgrade.

Comment thread vllm_ascend/attention/attention_v1.py
Comment thread vllm_ascend/attention/mla_v1.py
Comment thread vllm_ascend/core/scheduler.py
Comment thread vllm_ascend/distributed/mooncake/config_data.py
Comment thread vllm_ascend/patch/platform/patch_mamba_config.py
Comment thread vllm_ascend/torchair/torchair_mla.py
Comment thread vllm_ascend/torchair/torchair_sfa.py
Comment thread vllm_ascend/worker/block_table.py
Comment thread vllm_ascend/worker/model_runner_v1.py
Comment thread vllm_ascend/worker/worker_v1.py
@22dimensions 22dimensions force-pushed the update branch 4 times, most recently from c1e61fb to 840da0d Compare November 5, 2025 09:46
@MengqingCao MengqingCao added ready read for review ready-for-test start test by label for PR labels Nov 6, 2025
@github-actions github-actions Bot added the documentation Improvements or additions to documentation label Nov 11, 2025
@github-actions github-actions Bot removed the documentation Improvements or additions to documentation label Nov 11, 2025
@github-actions github-actions Bot added the documentation Improvements or additions to documentation label Nov 11, 2025
@22dimensions 22dimensions changed the title [WIP] Upgrade to 0.11.1 newest vllm commit Upgrade to 0.11.1 newest vllm commit Nov 11, 2025
@22dimensions 22dimensions force-pushed the update branch 2 times, most recently from 43c4366 to c8f1b00 Compare November 12, 2025 02:51
Signed-off-by: 22dimensions <waitingwind@foxmail.com>
@wangxiyuan wangxiyuan merged commit c272747 into vllm-project:main Nov 12, 2025
26 checks passed
luolun pushed a commit to luolun/vllm-ascend that referenced this pull request Nov 19, 2025
### What this PR does / why we need it?
adapt vllm-ascend main branch with vllm releases/v0.11.1

fix `forward context not set` in test_vlm.py caused by:
vllm-project/vllm#23207

fix import `cdiv round` failed caused by:
vllm-project/vllm#27188

fix import `init_cached_hf_modules` failed caused by:
vllm-project/vllm#27567

adapt triton kernel `fused_recurrent_gated_delta_rule_fwd_kernel` caused
by: vllm-project/vllm#27654
- remove unused code in sigmoid_gating.py
- `class FusedRecurrentFunction` , `fused_recurrent_gated_delta_rule`,
`fused_recurrent_gated_delta_rule_fwd`

### Does this PR introduce _any_ user-facing change?
No

### How was this patch tested?
CI 


- vLLM version: v0.11.0
- vLLM main:
vllm-project/vllm@83f478b

Signed-off-by: 22dimensions <waitingwind@foxmail.com>
Signed-off-by: luolun <luolun1995@cmbchina.com>
hwhaokun pushed a commit to hwhaokun/vllm-ascend that referenced this pull request Nov 19, 2025
### What this PR does / why we need it?
adapt vllm-ascend main branch with vllm releases/v0.11.1

fix `forward context not set` in test_vlm.py caused by:
vllm-project/vllm#23207

fix import `cdiv round` failed caused by:
vllm-project/vllm#27188

fix import `init_cached_hf_modules` failed caused by:
vllm-project/vllm#27567

adapt triton kernel `fused_recurrent_gated_delta_rule_fwd_kernel` caused
by: vllm-project/vllm#27654
- remove unused code in sigmoid_gating.py
- `class FusedRecurrentFunction` , `fused_recurrent_gated_delta_rule`,
`fused_recurrent_gated_delta_rule_fwd`

### Does this PR introduce _any_ user-facing change?
No

### How was this patch tested?
CI

- vLLM version: v0.11.0
- vLLM main:
vllm-project/vllm@83f478b

Signed-off-by: 22dimensions <waitingwind@foxmail.com>
Signed-off-by: hwhaokun <haokun0405@163.com>
NSDie pushed a commit to NSDie/vllm-ascend that referenced this pull request Nov 24, 2025
### What this PR does / why we need it?
adapt vllm-ascend main branch with vllm releases/v0.11.1

fix `forward context not set` in test_vlm.py caused by:
vllm-project/vllm#23207

fix import `cdiv round` failed caused by:
vllm-project/vllm#27188

fix import `init_cached_hf_modules` failed caused by:
vllm-project/vllm#27567

adapt triton kernel `fused_recurrent_gated_delta_rule_fwd_kernel` caused
by: vllm-project/vllm#27654
- remove unused code in sigmoid_gating.py
- `class FusedRecurrentFunction` , `fused_recurrent_gated_delta_rule`,
`fused_recurrent_gated_delta_rule_fwd`

### Does this PR introduce _any_ user-facing change?
No

### How was this patch tested?
CI

- vLLM version: v0.11.0
- vLLM main:
vllm-project/vllm@83f478b

Signed-off-by: 22dimensions <waitingwind@foxmail.com>
Signed-off-by: nsdie <yeyifan@huawei.com>
Clorist33 pushed a commit to Clorist33/vllm-ascend that referenced this pull request Dec 10, 2025
### What this PR does / why we need it?
adapt vllm-ascend main branch with vllm releases/v0.11.1

fix `forward context not set` in test_vlm.py caused by:
vllm-project/vllm#23207

fix import `cdiv round` failed caused by:
vllm-project/vllm#27188

fix import `init_cached_hf_modules` failed caused by:
vllm-project/vllm#27567

adapt triton kernel `fused_recurrent_gated_delta_rule_fwd_kernel` caused
by: vllm-project/vllm#27654
- remove unused code in sigmoid_gating.py
- `class FusedRecurrentFunction` , `fused_recurrent_gated_delta_rule`,
`fused_recurrent_gated_delta_rule_fwd`

### Does this PR introduce _any_ user-facing change?
No

### How was this patch tested?
CI 


- vLLM version: v0.11.0
- vLLM main:
vllm-project/vllm@83f478b

Signed-off-by: 22dimensions <waitingwind@foxmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

documentation Improvements or additions to documentation module:ops module:tests ready read for review ready-for-test start test by label for PR

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants