vLLM fakequant: add recipe-based quantization support#1233
Open
kinjalpatel27 wants to merge 2 commits intomainfrom
Open
vLLM fakequant: add recipe-based quantization support#1233kinjalpatel27 wants to merge 2 commits intomainfrom
kinjalpatel27 wants to merge 2 commits intomainfrom
Conversation
Signed-off-by: Kinjal Patel <kinjalpravin@nvidia.com>
|
Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually. Contributors can view more details about this message here. |
Contributor
|
Important Pre-merge checks failedPlease resolve all errors before merging. Addressing warnings is optional. ❌ Failed checks (1 error)
✅ Passed checks (3 passed)
✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Comment |
Contributor
|
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #1233 +/- ##
==========================================
+ Coverage 76.03% 77.58% +1.54%
==========================================
Files 350 350
Lines 40469 40537 +68
==========================================
+ Hits 30772 31449 +677
+ Misses 9697 9088 -609
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@examples/vllm_serve/vllm_ptq_utils.py`:
- Around line 145-150: Replace the unsafe assert in the recipe validation with
an explicit runtime check: after calling
load_recipe(quant_config["recipe_path"]) and assigning to recipe, verify type
with if not isinstance(recipe, ModelOptPTQRecipe): raise a ValueError containing
the same descriptive message (including the actual type and recipe path) and
then set quant_cfg = recipe.quantize; this ensures load_recipe,
ModelOptPTQRecipe, quant_cfg and recipe behavior remains the same but prevents
the check from being skipped under Python optimizations.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
Run ID: fe9bb658-ad3b-4a06-aa28-6e2bb5155f6f
📒 Files selected for processing (4)
examples/vllm_serve/README.mdexamples/vllm_serve/fakequant_worker.pyexamples/vllm_serve/vllm_ptq_utils.pyexamples/vllm_serve/vllm_serve_fakequant.py
Comment on lines
+145
to
+150
| if quant_config["recipe_path"]: | ||
| recipe = load_recipe(quant_config["recipe_path"]) | ||
| assert isinstance(recipe, ModelOptPTQRecipe), ( | ||
| f"Expected PTQ recipe, but got {type(recipe).__name__} from {quant_config['recipe_path']}" | ||
| ) | ||
| quant_cfg = recipe.quantize |
Contributor
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
# Verify current assertion usage in this path.
rg -n -C2 'assert isinstance\(recipe, ModelOptPTQRecipe\)' --type=py
# Demonstrate Python optimization removing assert checks.
python - <<'PY'
src = """def f(x):
assert isinstance(x, int), "bad type"
return x
"""
ns = {}
exec(compile(src, "<inline>", "exec", optimize=1), ns)
import dis
dis.dis(ns["f"])
PYRepository: NVIDIA/Model-Optimizer
Length of output: 1818
Use explicit exception instead of assert for runtime validation.
At line 147, using assert isinstance() is unsafe because assertions can be disabled when Python runs with optimization flags (e.g., python -O), allowing invalid recipe types to bypass this check silently. Use an explicit if/raise ValueError() pattern instead.
Proposed fix
if quant_config["recipe_path"]:
recipe = load_recipe(quant_config["recipe_path"])
- assert isinstance(recipe, ModelOptPTQRecipe), (
- f"Expected PTQ recipe, but got {type(recipe).__name__} from {quant_config['recipe_path']}"
- )
+ if not isinstance(recipe, ModelOptPTQRecipe):
+ raise ValueError(
+ f"Expected PTQ recipe, but got {type(recipe).__name__} from {quant_config['recipe_path']}"
+ )
quant_cfg = recipe.quantize📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| if quant_config["recipe_path"]: | |
| recipe = load_recipe(quant_config["recipe_path"]) | |
| assert isinstance(recipe, ModelOptPTQRecipe), ( | |
| f"Expected PTQ recipe, but got {type(recipe).__name__} from {quant_config['recipe_path']}" | |
| ) | |
| quant_cfg = recipe.quantize | |
| if quant_config["recipe_path"]: | |
| recipe = load_recipe(quant_config["recipe_path"]) | |
| if not isinstance(recipe, ModelOptPTQRecipe): | |
| raise ValueError( | |
| f"Expected PTQ recipe, but got {type(recipe).__name__} from {quant_config['recipe_path']}" | |
| ) | |
| quant_cfg = recipe.quantize |
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@examples/vllm_serve/vllm_ptq_utils.py` around lines 145 - 150, Replace the
unsafe assert in the recipe validation with an explicit runtime check: after
calling load_recipe(quant_config["recipe_path"]) and assigning to recipe, verify
type with if not isinstance(recipe, ModelOptPTQRecipe): raise a ValueError
containing the same descriptive message (including the actual type and recipe
path) and then set quant_cfg = recipe.quantize; this ensures load_recipe,
ModelOptPTQRecipe, quant_cfg and recipe behavior remains the same but prevents
the check from being skipped under Python optimizations.
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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 does this PR do?
Type of change: example update
This PR adds recipe-based quantization support to the vLLM fakequant example.
Testing
Before your PR is "Ready for review"
Make sure you read and follow Contributor guidelines and your commits are signed (
git commit -s -S).Make sure you read and follow the Security Best Practices (e.g. avoiding hardcoded
trust_remote_code=True,torch.load(..., weights_only=False),pickle, etc.).CONTRIBUTING.md: N/AAdditional Information
Summary by CodeRabbit
New Features
RECIPE_PATHenvironment variable support enabling users to specify ModelOpt PTQ recipe YAML files for quantization configuration in vLLM serving.Documentation