Skip to content

[ChatQnA] Remove enforce-eager to enable HPU graphs for better vLLM perf #1210

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
lvliang-intel merged 4 commits into from
Dec 10, 2024
Merged

[ChatQnA] Remove enforce-eager to enable HPU graphs for better vLLM perf #1210

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
ed333c3
remove enforce-eager to enable HPU graphs
wangkl2 Nov 28, 2024
44ca7fd
Merge branch 'main' into update-vllm-gaudi
wangkl2 Dec 9, 2024
68448e1
Merge branch 'opea-project:main' into update-vllm-gaudi
wangkl2 Dec 10, 2024
18ffa62
Increase the llm max timeout in ci for fully warmup
wangkl2 Dec 10, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion ChatQnA/docker_compose/intel/hpu/gaudi/compose_vllm.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -97,7 +97,7 @@ services:
cap_add:
- SYS_NICE
ipc: host
command: --enforce-eager --model $LLM_MODEL_ID --tensor-parallel-size 1 --host 0.0.0.0 --port 80 --block-size 128 --max-num-seqs 256 --max-seq_len-to-capture 2048
command: --model $LLM_MODEL_ID --tensor-parallel-size 1 --host 0.0.0.0 --port 80 --block-size 128 --max-num-seqs 256 --max-seq_len-to-capture 2048
chatqna-gaudi-backend-server:
image: ${REGISTRY:-opea}/chatqna:${TAG:-latest}
container_name: chatqna-gaudi-backend-server
Expand Down
1 change: 0 additions & 1 deletion ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna-vllm.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1286,7 +1286,6 @@ spec:
type: RuntimeDefault
image: "opea/vllm-gaudi:latest"
args:
- "--enforce-eager"
- "--model"
- "$(MODEL_ID)"
- "--tensor-parallel-size"
Expand Down
Loading