[Feature]: Native GGUF+FP8 Quantization Support for DiT, after #1034 #4054
Artifacts
Produced during runtime
| Name | Size | Digest | |
|---|---|---|---|
|
vllm-omni-wheel-py3.11
|
826 KB |
sha256:b72466a88365bb318b1785823439446b674e68322c3a044b25074f8fe8a879c8
|
|
|
vllm-omni-wheel-py3.12
|
826 KB |
sha256:4cb2f9ae1b0735f391d8cb1c319f945b3a0a71a1fffaab5ea5fedbf3804e41c8
|
|