From 034686b178a49d1199c77e99d71a62333de19061 Mon Sep 17 00:00:00 2001 From: Mohit Sharma Date: Mon, 24 Jun 2024 15:20:45 +0000 Subject: [PATCH] update heading --- Makefile | 3 +++ docs/source/_toctree.yml | 2 +- 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/Makefile b/Makefile index a1399b6d..24dd4d6f 100644 --- a/Makefile +++ b/Makefile @@ -53,3 +53,6 @@ run-falcon-7b-instruct-quantize: clean: rm -rf target aml + +interact: + docker run --rm -it --cap-add=SYS_PTRACE --security-opt seccomp=unconfined --device=/dev/kfd --device=/dev/dri --group-add video --ipc=host --shm-size 64g --net host -v /home/mohit/.cache/huggingface/hub/:/data -v $(PWD):/tgi tgi-mht diff --git a/docs/source/_toctree.yml b/docs/source/_toctree.yml index 4bb735a3..cc215cae 100644 --- a/docs/source/_toctree.yml +++ b/docs/source/_toctree.yml @@ -44,7 +44,7 @@ - local: basic_tutorials/train_medusa title: Train Medusa - local: basic_tutorials/fp8_kv_cache - title: Accelerating Inference with FP8 KV Cache + title: FP8 KV Cache title: Tutorials - sections: - local: conceptual/streaming