Why PTPC-FP8 rocks:
- Per-Token Activation Scaling: Each token gets its own scaling factor
- Per-Channel Weight Scaling: Each weight column (output channel) gets its own scaling factor
Delivers FP8 speed with accuracy closer to BF16 – the best FP8 option for ROCm! [2/2]
- Per-Token Activation Scaling: Each token gets its own scaling factor
- Per-Channel Weight Scaling: Each weight column (output channel) gets its own scaling factor
Delivers FP8 speed with accuracy closer to BF16 – the best FP8 option for ROCm! [2/2]
March 22, 2025 at 11:47 AM
Why PTPC-FP8 rocks:
- Per-Token Activation Scaling: Each token gets its own scaling factor
- Per-Channel Weight Scaling: Each weight column (output channel) gets its own scaling factor
Delivers FP8 speed with accuracy closer to BF16 – the best FP8 option for ROCm! [2/2]
- Per-Token Activation Scaling: Each token gets its own scaling factor
- Per-Channel Weight Scaling: Each weight column (output channel) gets its own scaling factor
Delivers FP8 speed with accuracy closer to BF16 – the best FP8 option for ROCm! [2/2]
New Models:
- Idefics3 (VLM)
- H2OVL-Mississippi (VLM for OCR/docs!)
- Qwen2-Audio (Audio LLM)
- FalconMamba
- Florence-2 (VLM)
Plus new encoder-decoder embedding models like BERT, RoBERTa, XLM-RoBERTa.
- Idefics3 (VLM)
- H2OVL-Mississippi (VLM for OCR/docs!)
- Qwen2-Audio (Audio LLM)
- FalconMamba
- Florence-2 (VLM)
Plus new encoder-decoder embedding models like BERT, RoBERTa, XLM-RoBERTa.
November 17, 2024 at 8:59 AM
New Models:
- Idefics3 (VLM)
- H2OVL-Mississippi (VLM for OCR/docs!)
- Qwen2-Audio (Audio LLM)
- FalconMamba
- Florence-2 (VLM)
Plus new encoder-decoder embedding models like BERT, RoBERTa, XLM-RoBERTa.
- Idefics3 (VLM)
- H2OVL-Mississippi (VLM for OCR/docs!)
- Qwen2-Audio (Audio LLM)
- FalconMamba
- Florence-2 (VLM)
Plus new encoder-decoder embedding models like BERT, RoBERTa, XLM-RoBERTa.