18 lines
679 B
Plaintext
18 lines
679 B
Plaintext
Llama-4-Scout-Fp8-CT-vllm-cutlass.yaml
|
|
Llama-4-Scout-Fp8-ModelOpt-fi-trtllm.yaml
|
|
Qwen3-30B-A3B-Fp8-AutoFp8-fi-trtllm.yaml
|
|
Qwen3-30B-A3B-NvFp4-CT-vllm-cutlass.yaml
|
|
Qwen3-30B-A3B-NvFp4-CT-marlin.yaml
|
|
Qwen3-30B-A3B-NvFp4-CT-fi-trtllm.yaml
|
|
Qwen3-30B-A3B-NvFp4-CT-fi-cutlass.yaml
|
|
Qwen3-30B-A3B-NvFp4-ModelOpt-vllm-cutlass.yaml
|
|
Qwen3-30B-A3B-NvFp4-ModelOpt-marlin.yaml
|
|
Qwen3-30B-A3B-NvFp4-ModelOpt-fi-trtllm.yaml
|
|
Qwen3-30B-A3B-NvFp4-ModelOpt-fi-cutlass.yaml
|
|
Llama-4-Scout-BF16-fi-cutlass.yaml
|
|
Llama-4-Scout-BF16-triton.yaml
|
|
Mixtral-8x7B-BF16-fi-cutlass.yaml
|
|
Mixtral-8x7B-BF16-triton.yaml
|
|
Nemotron-Nano-30B-Fp8-ModelOpt-fi-trtllm.yaml
|
|
Nemotron-Nano-30B-NvFp4-ModelOpt-fi-cutlass.yaml
|