main
txt 19 lines 771 Bytes
Raw
1 Llama-4-Scout-Fp8-CT-vllm-cutlass.yaml
2 Llama-4-Scout-Fp8-ModelOpt-fi-trtllm.yaml
3 Qwen3-30B-A3B-Fp8-AutoFp8-fi-trtllm.yaml
4 Qwen3-30B-A3B-NvFp4-CT-vllm-cutlass.yaml
5 Qwen3-30B-A3B-NvFp4-CT-marlin.yaml
6 Qwen3-30B-A3B-NvFp4-CT-fi-trtllm.yaml
7 Qwen3-30B-A3B-NvFp4-CT-fi-cutlass.yaml
8 Qwen3-30B-A3B-NvFp4-ModelOpt-vllm-cutlass.yaml
9 Qwen3-30B-A3B-NvFp4-ModelOpt-marlin.yaml
10 Qwen3-30B-A3B-NvFp4-ModelOpt-fi-trtllm.yaml
11 Qwen3-30B-A3B-NvFp4-ModelOpt-fi-cutlass.yaml
12 Llama-4-Scout-BF16-fi-cutlass.yaml
13 Llama-4-Scout-BF16-triton.yaml
14 Mixtral-8x7B-BF16-fi-cutlass.yaml
15 Mixtral-8x7B-BF16-triton.yaml
16 Nemotron-Nano-30B-Fp8-ModelOpt-fi-trtllm.yaml
17 Nemotron-Nano-30B-NvFp4-ModelOpt-fi-cutlass.yaml
18 Nemotron-Nano-30B-NvFp4-ModelOpt-vllm-cutlass.yaml
19 DeepSeek-V4-Flash-deepgemm-mega-moe.yaml