[Fix] Fix gpu_model_runner req_state update error for issue 283 #291
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Outdated suggestions cannot be applied.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.
Purpose
What this PR does / why we need it?
Apply the merged pr vllm-project/vllm#19330 to support load failure
Modifications
Does this PR introduce any user-facing change?
Adapt to the vllm main code and support load failure handling.
Test
How was this patch tested?
Tested with offline script, manually construct normal load/load failure/preemption scenarios.


Compare kvcache they loaded. The preemption load same kv cache. When loading failed, it would generate outputs without uc connector.