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 7, 04:00 UTC
docs: fix wrong cc in int8.md (#36209)
Signed-off-by: Xiang Shi <realkevin@tutanota.com>
Xiang Shi committed
Mar 6, 2026 at 14:01 UTC
e68de8adc0301babb3bb3fcd2ddccaf98e7695c8
1 file changed
+1
-1
docs/features/quantization/int8.md
+1
-1
@@ -9,7 +9,7 @@ Please visit the HF collection of [quantized INT8 checkpoints of popular LLMs re
9
INT8 computation is supported on NVIDIA GPUs with compute capability > 7.5 (Turing, Ampere, Ada Lovelace, Hopper).
10
11
!!! warning
12
- **Blackwell GPU Limitation**: INT8 is not supported on compute capability >= 100 (e.g., RTX 6000 Blackwell).
12
+ **Blackwell GPU Limitation**: INT8 is not supported on compute capability >= 10.0 (e.g., RTX 6000 Blackwell).
13
Use [FP8 quantization](fp8.md) instead, or run on Hopper/Ada/Ampere architectures.
14
15
## Prerequisites