From 8384badc69c219c51918c70ac5e7eb8528253b3e Mon Sep 17 00:00:00 2001 From: lusipad Date: Thu, 13 Feb 2025 07:27:27 +0800 Subject: [PATCH] doc: fix clerical error --- doc/en/DeepseekR1_V3_tutorial.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/doc/en/DeepseekR1_V3_tutorial.md b/doc/en/DeepseekR1_V3_tutorial.md index f5c4972..0d11c8b 100644 --- a/doc/en/DeepseekR1_V3_tutorial.md +++ b/doc/en/DeepseekR1_V3_tutorial.md @@ -24,7 +24,7 @@ # SUMMARY -> **Fed 10, 2025**: Support DeepseekR1 and V3 on single (24GB VRAM)/multi gpu and 382G DRAM, up to 3~28x speedup.
+> **Feb 10, 2025**: Support DeepseekR1 and V3 on single (24GB VRAM)/multi gpu and 382G DRAM, up to 3~28x speedup.
Hi, we're the KTransformers team (formerly known for our local CPU/GPU hybrid inference open source project with DeepSeek-V2). @@ -175,4 +175,4 @@ Intel is currently the only CPU vendor that supports AMX-like instructions, whic Attention! If you are testing R1 and it may skip thinking. So you can add arg: `--force_think true`. The detail is in [FAQ](./FAQ.md) part
### More FAQ -[See detail](./FAQ.md) \ No newline at end of file +[See detail](./FAQ.md)