Mirror
/
LocalAI
mirror of https://github.com/mudler/LocalAI.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Bump oneapi-basekit, optimum and openvino (#2139) 

* Bump oneapi-basekit, optimum and openvino

* Changed PERFORMANCE HINT to CUMULATIVE_THROUGHPUT

Minor latency change for first token but about 10-15% speedup on token generation.
This commit is contained in:
fakezeta 2024-04-26 16:20:43 +02:00 committed by GitHub
parent 006306b183
commit c9451cb604
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
5 changed files with 15 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
.github/workflows/image-pr.yml vendored
View File

@ -68,7 +68,7 @@ jobs:
- build-type: 'sycl_f16'
platforms: 'linux/amd64'
tag-latest: 'false'
base-image: "intel/oneapi-basekit:2024.0.1-devel-ubuntu22.04"
base-image: "intel/oneapi-basekit:2024.1.0-devel-ubuntu22.04"
grpc-base-image: "ubuntu:22.04"
tag-suffix: 'sycl-f16-ffmpeg'
ffmpeg: 'true'
@ -110,7 +110,7 @@ jobs:
- build-type: 'sycl_f16'
platforms: 'linux/amd64'
tag-latest: 'false'
base-image: "intel/oneapi-basekit:2024.0.1-devel-ubuntu22.04"
base-image: "intel/oneapi-basekit:2024.1.0-devel-ubuntu22.04"
grpc-base-image: "ubuntu:22.04"
tag-suffix: 'sycl-f16-ffmpeg-core'
ffmpeg: 'true'

12
.github/workflows/image.yml vendored
View File

@ -148,7 +148,7 @@ jobs:
- build-type: 'sycl_f16'
platforms: 'linux/amd64'
tag-latest: 'auto'
base-image: "intel/oneapi-basekit:2024.0.1-devel-ubuntu22.04"
base-image: "intel/oneapi-basekit:2024.1.0-devel-ubuntu22.04"
grpc-base-image: "ubuntu:22.04"
tag-suffix: '-sycl-f16-ffmpeg'
ffmpeg: 'true'
@ -161,7 +161,7 @@ jobs:
- build-type: 'sycl_f32'
platforms: 'linux/amd64'
tag-latest: 'auto'
base-image: "intel/oneapi-basekit:2024.0.1-devel-ubuntu22.04"
base-image: "intel/oneapi-basekit:2024.1.0-devel-ubuntu22.04"
grpc-base-image: "ubuntu:22.04"
tag-suffix: '-sycl-f32-ffmpeg'
ffmpeg: 'true'
@ -175,7 +175,7 @@ jobs:
- build-type: 'sycl_f16'
platforms: 'linux/amd64'
tag-latest: 'false'
base-image: "intel/oneapi-basekit:2024.0.1-devel-ubuntu22.04"
base-image: "intel/oneapi-basekit:2024.1.0-devel-ubuntu22.04"
grpc-base-image: "ubuntu:22.04"
tag-suffix: '-sycl-f16-core'
ffmpeg: 'false'
@ -185,7 +185,7 @@ jobs:
- build-type: 'sycl_f32'
platforms: 'linux/amd64'
tag-latest: 'false'
base-image: "intel/oneapi-basekit:2024.0.1-devel-ubuntu22.04"
base-image: "intel/oneapi-basekit:2024.1.0-devel-ubuntu22.04"
grpc-base-image: "ubuntu:22.04"
tag-suffix: '-sycl-f32-core'
ffmpeg: 'false'
@ -195,7 +195,7 @@ jobs:
- build-type: 'sycl_f16'
platforms: 'linux/amd64'
tag-latest: 'false'
base-image: "intel/oneapi-basekit:2024.0.1-devel-ubuntu22.04"
base-image: "intel/oneapi-basekit:2024.1.0-devel-ubuntu22.04"
grpc-base-image: "ubuntu:22.04"
tag-suffix: '-sycl-f16-ffmpeg-core'
ffmpeg: 'true'
@ -205,7 +205,7 @@ jobs:
- build-type: 'sycl_f32'
platforms: 'linux/amd64'
tag-latest: 'false'
base-image: "intel/oneapi-basekit:2024.0.1-devel-ubuntu22.04"
base-image: "intel/oneapi-basekit:2024.1.0-devel-ubuntu22.04"
grpc-base-image: "ubuntu:22.04"
tag-suffix: '-sycl-f32-ffmpeg-core'
ffmpeg: 'true'

4
Makefile
View File

@ -707,7 +707,7 @@ docker-aio-all:
docker-image-intel:
docker build \
--build-arg BASE_IMAGE=intel/oneapi-basekit:2024.0.1-devel-ubuntu22.04 \
--build-arg BASE_IMAGE=intel/oneapi-basekit:2024.1.0-devel-ubuntu22.04 \
--build-arg IMAGE_TYPE=$(IMAGE_TYPE) \
--build-arg GO_TAGS="none" \
--build-arg MAKEFLAGS="$(DOCKER_MAKEFLAGS)" \
@ -715,7 +715,7 @@ docker-image-intel:
docker-image-intel-xpu:
docker build \
--build-arg BASE_IMAGE=intel/oneapi-basekit:2024.0.1-devel-ubuntu22.04 \
--build-arg BASE_IMAGE=intel/oneapi-basekit:2024.1.0-devel-ubuntu22.04 \
--build-arg IMAGE_TYPE=$(IMAGE_TYPE) \
--build-arg GO_TAGS="none" \
--build-arg MAKEFLAGS="$(DOCKER_MAKEFLAGS)" \

7
backend/python/common-env/transformers/transformers.yml
View File

@ -60,9 +60,10 @@ dependencies:
- networkx
- numpy==1.26.0
- onnx==1.15.0
- openvino==2024.0.0
- openvino-telemetry==2023.2.1
- optimum[openvino]==1.17.1
- openvino==2024.1.0
- openvino-telemetry==2024.1.0
- optimum[openvino]==1.19.1
- optimum-intel==1.16.1
- packaging==23.2
- pandas
- peft==0.5.0

2
backend/python/transformers/transformers_server.py
View File

@ -150,7 +150,7 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
self.model = OVModelForCausalLM.from_pretrained(model_name,
compile=True,
trust_remote_code=request.TrustRemoteCode,
ov_config={"PERFORMANCE_HINT": "LATENCY"},
ov_config={"PERFORMANCE_HINT": "CUMULATIVE_THROUGHPUT"},
device=device_map)
self.OV = True
else: