A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 14:45 UTC
Update supported_hardware.md for TPU INT8 (#16437)
Michael Goin committed
Apr 10, 2025 at 22:28 UTC
ed37599544007fdbd1c6a33d2a2b50f5df6764ee
1 file changed
+1
-1
docs/source/features/quantization/supported_hardware.md
+1
-1
@@ -62,7 +62,7 @@ The table below shows the compatibility of various quantization implementations
62
* ❌
63
* ✅︎
64
* ❌
65
- * ❌
65
+ * ✅︎
66
- * FP8 (W8A8)
67
* ❌
68
* ❌