[Hardware][Intel] Isolate CPUModelRunner and ModelRunner for better maintenance #3824
Conversation
There was a problem hiding this comment.
@bigPYJ1151 Thanks for the PR! Could you please rebase the PR before merge?
| @@ -141,7 +141,7 @@ def forward( | |||
| attn_metadata.kv_cache_dtype) | |||
|
|
|||
| if attn_metadata.is_prompt: | |||
| if (kv_cache is None or attn_metadata.block_tables.numel() == 0): | |||
| if (kv_cache is None or attn_metadata.block_tables is None): | |||
There was a problem hiding this comment.
| if (kv_cache is None or attn_metadata.block_tables is None): | |
| if kv_cache is None or attn_metadata.block_tables is None: |
| bias = bias[None, :].expand(num_heads, prompt_len, prompt_len)\ | ||
| .mul(alibi_slopes[:, None, None]) |
There was a problem hiding this comment.
Why do we change this?
There was a problem hiding this comment.
Because expand outputs a tensor view doesn't support inplace operation.
vllm/worker/cpu_model_runner.py
Outdated
There was a problem hiding this comment.
Thanks for factoring out this part from GPU model runner. We will work on reducing the duplicated code in the future.
bigPYJ1151
force-pushed
the
cpu_backend_seperate
branch
from
24a5a18
to
c7882fa
Compare
|
Hi @WoosukKwon thanks for your comments, this PR is ready to merge. BTW, the chunked prefill enabled in #3884 looks good, and it made some changes in |
|
Should we create a new issue to track the deduplication? That much duplicated code makes me feel a bit uneasy lol |
Fix #3776
This PR created a new
CPUModelRunnerfromModelRunnerfor better maintenance.PR Checklist (Click to Expand)
Thank you for your contribution to vLLM! Before submitting the pull request, please ensure the PR meets the following criteria. This helps vLLM maintain the code quality and improve the efficiency of the review process.
PR Title and Classification
Only specific types of PRs will be reviewed. The PR title is prefixed appropriately to indicate the type of change. Please use one of the following:
[Bugfix]for bug fixes.[CI/Build]for build or continuous integration improvements.[Doc]for documentation fixes and improvements.[Model]for adding a new model or improving an existing model. Model name should appear in the title.[Frontend]For changes on the vLLM frontend (e.g., OpenAI API server,LLMclass, etc.)[Kernel]for changes affecting CUDA kernels or other compute kernels.[Core]for changes in the core vLLM logic (e.g.,LLMEngine,AsyncLLMEngine,Scheduler, etc.)[Hardware][Vendor]for hardware-specific changes. Vendor name should appear in the prefix (e.g.,[Hardware][AMD]).[Misc]for PRs that do not fit the above categories. Please use this sparingly.Note: If the PR spans more than one category, please include all relevant prefixes.
Code Quality
The PR need to meet the following code quality standards:
format.shto format your code.docs/source/if the PR modifies the user-facing behaviors of vLLM. It helps vLLM user understand and utilize the new features or changes.Notes for Large Changes
Please keep the changes as concise as possible. For major architectural changes (>500 LOC excluding kernel/data/config/test), we would expect a GitHub issue (RFC) discussing the technical design and justification. Otherwise, we will tag it with
rfc-requiredand might not go through the PR.What to Expect for the Reviews
The goal of the vLLM team is to be a transparent reviewing machine. We would like to make the review process transparent and efficient and make sure no contributor feel confused or frustrated. However, the vLLM team is small, so we need to prioritize some PRs over others. Here is what you can expect from the review process:
action-requiredlabel on the PR if there are changes required. The contributor should address the comments and ping the reviewer to re-review the PR.Thank You
Finally, thank you for taking the time to read these guidelines and for your interest in contributing to vLLM. Your contributions make vLLM a great tool for everyone!