vllm-project/guidellm

Default `mp_context_type="fork"` segfaults all workers on macOS (supported platform); actionable hint was removed from the error message 8 days ago

good first issue priority-high

1.5K

Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs

Python

Benchmark hangs forever (scheduler/worker deadlock) when dataset has no mappable columns — should fail fast instead 2 months ago

good first issue bug escape

vllm-project/guidellm

1.5K

Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs

Python

TypeError: Object of type PosixPath is not JSON serializable when saving benchmark report with --output-dir 2 months ago

good first issue priority-high bug escape

vllm-project/guidellm

1.5K

Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs

Python

Define effective hierarchy of debug logging 7 months ago

good first issue priority-low internal

vllm-project/guidellm

1.5K

Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs

Python

[Feature Request] List as input for max-seconds and max-requests 7 months ago

good first issue internal

vllm-project/guidellm

1.5K

Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs

Python

Improve error handling around invalid tokenizer names 7 months ago

good first issue internal needs followup

vllm-project/guidellm

1.5K

Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs

Python

Can you list some popular HuggingFace datasets that we can used to set guidellm --data 8 months ago

documentation good first issue

vllm-project/guidellm

1.5K

Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs

Python

ModuleNotFoundError: No module named 'transformers.tokenization_utils' 8 months ago

good first issue bug

vllm-project/guidellm

1.5K

Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs

Python

Add support for a Python vLLM backend about 1 year ago

good first issue priority-high internal

vllm-project/guidellm

1.5K

Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs

Python

Open Issues Need Help