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, LLM
class, 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:
- We adhere to Google Python
style guide and Google C++
style guide.
- Pass all linter checks. Please use
format.sh
to format your code.
- The code need to be well-documented to ensure future contributors
can easily understand the code.
- Include sufficient tests to ensure the project to stay correct and
robust. This includes both unit tests and integration tests.
- Please add documentation to
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-required
and 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:
- After the PR is submitted, the PR will be assigned to a reviewer.
Every reviewer will pick up the PRs based on their expertise and
availability.
- After the PR is assigned, the reviewer will provide status update
every 2-3 days. If the PR is not reviewed within 7 days, please feel
free to ping the reviewer or the vLLM team.
- After the review, the reviewer will put an
action-required
label on the PR if there are changes required.
The contributor should address the comments and ping the reviewer to
re-review the PR.
- Please respond to all comments within a reasonable time frame. If a
comment isn't clear or you disagree with a suggestion, feel free to ask
for clarification or discuss the suggestion.
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!
---
README_GAUDI.md | 3 +-
.../getting_started/gaudi-installation.rst | 3 +-
vllm/attention/backends/habana_attn.py | 26 +++-
vllm/attention/ops/habana_paged_attn.py | 10 ++
vllm/config.py | 8 +-
vllm/engine/arg_utils.py | 14 ++-
vllm/engine/llm_engine.py | 6 +-
vllm/entrypoints/llm.py | 3 +
vllm/executor/habana_executor.py | 9 ++
vllm/executor/ray_habana_executor.py | 3 +
vllm/hpu/cache_ops.py | 31 +++++
vllm/hpu/ops.py | 33 +++--
vllm/hpu/utils.py | 40 ++++++
vllm/model_executor/layers/layernorm.py | 11 +-
vllm/model_executor/layers/linear.py | 10 +-
.../layers/quantization/__init__.py | 2 +
.../model_executor/layers/quantization/inc.py | 115 ++++++++++++++++++
vllm/model_executor/model_loader/loader.py | 22 ++--
vllm/model_executor/models/llama.py | 6 +
vllm/utils.py | 1 +
vllm/worker/cache_engine.py | 4 +-
vllm/worker/habana_model_runner.py | 57 ++++++++-
vllm/worker/habana_worker.py | 21 ++++
23 files changed, 387 insertions(+), 51 deletions(-)
create mode 100644 vllm/model_executor/layers/quantization/inc.py
diff --git a/README_GAUDI.md b/README_GAUDI.md
index a569d6314acf8..9ea30a2e43f69 100644
--- a/README_GAUDI.md
+++ b/README_GAUDI.md
@@ -26,7 +26,8 @@ To verify that the Intel Gaudi software was correctly installed, run:
``` {.console}
$ hl-smi # verify that hl-smi is in your PATH and each Gaudi accelerator is visible
$ apt list --installed | grep habana # verify that habanalabs-firmware-tools, habanalabs-graph, habanalabs-rdma-core and habanalabs-thunk are installed
-$ pip list | habana # verify that habana-torch-plugin, habana-torch-dataloader, habana-pyhlml, habana-media-loader and habana_quantization_toolkit are installed
+$ pip list | grep habana # verify that habana-torch-plugin, habana-torch-dataloader, habana-pyhlml and habana-media-loader are installed
+$ pip list | grep neural # verify that neural-compressor is installed
```
Refer to [Intel Gaudi Software Stack
diff --git a/docs/source/getting_started/gaudi-installation.rst b/docs/source/getting_started/gaudi-installation.rst
index 7af291d62efc6..ddbac022a8d9d 100644
--- a/docs/source/getting_started/gaudi-installation.rst
+++ b/docs/source/getting_started/gaudi-installation.rst
@@ -26,7 +26,8 @@ To verify that the Intel Gaudi software was correctly installed, run:
$ hl-smi # verify that hl-smi is in your PATH and each Gaudi accelerator is visible
$ apt list --installed | grep habana # verify that habanalabs-firmware-tools, habanalabs-graph, habanalabs-rdma-core and habanalabs-thunk are installed
- $ pip list | habana # verify that habana-torch-plugin, habana-torch-dataloader, habana-pyhlml, habana-media-loader and habana_quantization_toolkit are installed
+ $ pip list | grep habana # verify that habana-torch-plugin, habana-torch-dataloader, habana-pyhlml and habana-media-loader are installed
+ $ pip list | grep neural # verify that neural_compressor is installed
Refer to `Intel Gaudi Software Stack
Verification