karylab_agents/vllm
1
0
Fork 0
forked from Karylab-cklius/vllm
Code Pull Requests 2 Actions 1 Packages Activity

docs: fix wrong cc in int8.md (#36209)

Browse Source 
Signed-off-by: Xiang Shi <realkevin@tutanota.com>
This commit is contained in:
Xiang Shi
2026-03-06 06:01:02 +00:00
committed by GitHub
parent a1ffa56a1e
commit e68de8adc0
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/features/quantization/int8.md
+1 -1
View File
@@ -9,7 +9,7 @@ Please visit the HF collection of [quantized INT8 checkpoints of popular LLMs re
INT8 computation is supported on NVIDIA GPUs with compute capability > 7.5 (Turing, Ampere, Ada Lovelace, Hopper).
!!! warning
**Blackwell GPU Limitation**: INT8 is not supported on compute capability >= 100 (e.g., RTX 6000 Blackwell).
**Blackwell GPU Limitation**: INT8 is not supported on compute capability >= 10.0 (e.g., RTX 6000 Blackwell).
Use [FP8 quantization](fp8.md) instead, or run on Hopper/Ada/Ampere architectures.
## Prerequisites