GitLab

Bug description:
With torch 2.4.0.dev20240603+cu121,
cutlass_fp8_supported outputs False, and the (capability, version) before the comparison is (90, 11111111112)

This PR fixes the support check for FP8 CUTLASS ( cutlass_fp8_supported) which was introduced in https://github.com/vllm-project/vllm/pull/5183.

Co-authored-by: team <calvinn.ng@ahrefs.com>

Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>

Co-authored-by: Varun Sundar Rabindranath <varunsundar08@gmail.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>

Switching from torch._scaled_mm to vLLM's cutlass fp8 kernels when supported as we are seeing 5-15% improvement in e2e performance on neuralmagic/Meta-Llama-3-8B-Instruct-FP8

see https://docs.google.com/spreadsheets/d/1GiAnmzyGHgZ6zL_LDSTm35Bdrt4A8AaFEurDlISYYA4/ for some quick e2e benchmarks and #5144 for comparisons across different GEMM sizes.

Co-authored-by: mulin.lyh <mulin.lyh@taobao.com>

Co-authored-by: Simon Mo <simon.mo@hey.com>
Co-authored-by: Breno Faria <breno.faria@intrafind.com>

Co-authored-by: qiujiawei9 <qiujiawei9@jd.com>

[Frontend] OpenAI API server: Add `add_special_tokens` to ChatCompletionRequest (default False) (#5278)

This PR enables the fused topk_softmax kernel used in moe layer for HIP

Co-authored-by: mgoin <michael@neuralmagic.com>