mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-24 00:12:08 +00:00
update heading
This commit is contained in:
parent
e81c4cf863
commit
034686b178
3
Makefile
3
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
|
||||
|
@ -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
|
||||
|
Loading…
Reference in New Issue
Block a user