[INTEL-HPU] Deepseek R1 model enabling for Intel Gaudi

[xuechendi]

Accuracy is verified as below

VLLM_SKIP_WARMUP=true \
PT_HPU_ENABLE_LAZY_COLLECTIVES=true \
PT_HPU_WEIGHT_SHARING=0 \
VLLM_TEST_ENABLE_EP=1 \
VLLM_MLA_DISABLE_REQUANTIZATION=1 \
bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m deepseek-ai/DeepSeek-R1 -b 128 -l 256 -f 5 -t 8

3 options for running fp8 on HPU:

1. dynamic quant + static MOE => default option . Supported by public released hpu 1.20 synapse container
2. dynamic quant + dynamic MOE => enabled by "VLLM_DMOE_DYNAMIC_SCALE=1". Working with internal hpu synapse build and will release container later
3. static quant + dynamic MOE => enabled by using a converted model from original block-based quant to channel-based quant. Please refer https://github.com/HabanaAI/vllm-fork/blob/deepseek_r1/scripts/DEEPSEEK_R1_ON_GAUDI.md#option-3-run-with-static-quantization for instruction of how to convert model

[github-actions[bot]]

👋 Hi! Thank you for contributing to the vLLM project.

💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels.

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 either: Add ready label to the PR or enable auto-merge.

🚀

[mergify[bot]]

This pull request has merge conflicts that must be resolved before it can be merged. Please rebase the PR, @xuechendi.

https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork

[mergify[bot]]

This pull request has merge conflicts that must be resolved before it can be merged. Please rebase the PR, @xuechendi.

https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork

[xuechendi]

@mgoin @robertgshaw2-redhat @WoosukKwon @simon-mo @youkaichao @comaniac Would like to get some reviews, thanks

[mergify[bot]]

This pull request has merge conflicts that must be resolved before it can be merged. Please rebase the PR, @xuechendi.

https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork