huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 04:14:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

reset peak memory

Browse Source
This commit is contained in:
OlivierDehaene 2023-07-19 00:17:49 +02:00
parent 99568eef7b
commit 05d2a77e4c
2 changed files with 1 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
.github/workflows/build.yaml vendored
View File

@ -214,10 +214,6 @@ jobs:
- name: Install
run: |
make install-integration-tests
- name: Setup tmate session
uses: mxschmitt/action-tmate@v3
with:
limit-access-to-actor: true
- name: Run tests
run: |
export DOCKER_IMAGE=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:sha-${{ env.GITHUB_SHA_SHORT }}

1
server/text_generation_server/models/flash_causal_lm.py
View File

@ -714,6 +714,7 @@ class FlashCausalLM(Model):
global CACHE_MANAGER
torch.cuda.empty_cache()
torch.cuda.reset_peak_memory_stats(self.device)
try:
CACHE_MANAGER = CacheManager(
batch.blocks,