[Core] Integrate Fastsafetensor loader for loading model weights

[manish-sethi]

This PR integrates fastsafetensor library for loading model weights. Fastsafetensor uses GPU direct storage to load the weights directly from storage into GPU memory, making it faster as compared to reading parameters iteratively from file. See https://github.com/foundation-model-stack/fastsafetensors for more details.

Following are the experimental results for the time taken to load the weights from NVMe using the existing safetensor loader v/s fastsafetensor loader.

Model	Tensor_parallel	GPU	Time with safetensor loader(sec)	Time with fastsafetensor loader(sec)
Llama-2-7b-hf	1	A100	9	5
Llama-2-13b-hf	1	A100	19	9
Llama-2-13b-hf	2	A100	19	10
Llama-2-13b-hf	4	L40S	15	9

• The model files are loaded from storage, i.e., not present in the filesystem cache
• The time is for only loading the model weights within vLLM model initialization path

[github-actions]

👋 Hi! Thank you for contributing to the vLLM project.
Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can do one of these:

• Add ready label to the PR
• Enable auto-merge.

🚀