LM/Inference Engine Comparison: Difference between revisions

From Fundamental Ramen
< LM
Jump to navigation Jump to search
Created page with "{| class="wikitable" ! || Model format || TP || ROCM || XPU |- | vLLM || || || || |- | llama.cpp || || || || |- | SGLang || || || || |- | Strata || || || || |- | Ninfer || || || || |}"
 
No edit summary
 
Line 2: Line 2:
! || Model format || TP || ROCM || XPU
! || Model format || TP || ROCM || XPU
|-
|-
| vLLM || || || ||
| vLLM || Hugging Face Transformers / Safetensors || ✅ || ✅ || ✅
|-
|-
| llama.cpp || || || ||
| llama.cpp || GGUF || ✅ || ✅ || ✅
|-
|-
| SGLang || || || ||
| SGLang || Hugging Face Transformers / Safetensors || ✅ || ✅ || ✅
|-
|-
| Strata || || || ||
| Strata || Project-specific format / GGUF || ✅ || ✅ || ❌
|-
|-
| Ninfer || || || ||
| Ninfer || Project-specific model artifacts || ✅ || ✅ || ❌
|}
|}

Latest revision as of 09:01, 7 October 2026

Model format TP ROCM XPU
vLLM Hugging Face Transformers / Safetensors ✅ ✅ ✅
llama.cpp GGUF ✅ ✅ ✅
SGLang Hugging Face Transformers / Safetensors ✅ ✅ ✅
Strata Project-specific format / GGUF ✅ ✅ ❌
Ninfer Project-specific model artifacts ✅ ✅ ❌