"container/Dockerfile.trtllm" did not exist on "4fd4d53da0239e19d6d569634170985d11a32ab6"
Unverified Commit 8bd37c96 authored by Anant Sharma's avatar Anant Sharma Committed by GitHub
Browse files

refactor: move backend deploy, launch and slurm files from components to examples (#3849)


Signed-off-by: default avatarAnant Sharma <anants@nvidia.com>
parent 78359046
......@@ -39,7 +39,7 @@ spec:
extraPodSpec:
mainContainer:
image: my-registry/vllm-runtime:my-tag
workingDir: /workspace/components/backends/vllm
workingDir: /workspace/examples/backends/vllm
command:
- /bin/sh
- -c
......@@ -89,7 +89,7 @@ spec:
periodSeconds: 10
failureThreshold: 60
image: my-registry/vllm-runtime:my-tag
workingDir: /workspace/components/backends/vllm
workingDir: /workspace/examples/backends/vllm
command:
- /bin/sh
- -c
......@@ -139,7 +139,7 @@ spec:
periodSeconds: 10
failureThreshold: 60
image: my-registry/vllm-runtime:my-tag
workingDir: /workspace/components/backends/vllm
workingDir: /workspace/examples/backends/vllm
command:
- /bin/sh
- -c
......
......@@ -39,7 +39,7 @@ spec:
extraPodSpec:
mainContainer:
image: my-registry/vllm-runtime:my-tag
workingDir: /workspace/components/backends/vllm
workingDir: /workspace/examples/backends/vllm
command:
- /bin/sh
- -c
......@@ -89,7 +89,7 @@ spec:
periodSeconds: 10
failureThreshold: 60
image: my-registry/vllm-runtime:my-tag
workingDir: /workspace/components/backends/vllm
workingDir: /workspace/examples/backends/vllm
command:
- /bin/sh
- -c
......@@ -139,7 +139,7 @@ spec:
periodSeconds: 10
failureThreshold: 60
image: my-registry/vllm-runtime:my-tag
workingDir: /workspace/components/backends/vllm
workingDir: /workspace/examples/backends/vllm
command:
- /bin/sh
- -c
......
......@@ -30,7 +30,7 @@ class TestProfileSlaAiconfigurator:
self.model = ""
self.dgd_image = ""
self.backend = "trtllm"
self.config = "components/backends/trtllm/deploy/disagg.yaml"
self.config = "examples/backends/trtllm/deploy/disagg.yaml"
self.output_dir = "/tmp/test_profiling_results"
self.namespace = "test-namespace"
self.min_num_gpus_per_engine = 1
......
......@@ -46,7 +46,7 @@ class TestProfileSLADryRun:
class Args:
def __init__(self):
self.backend = "vllm"
self.config = "components/backends/vllm/deploy/disagg.yaml"
self.config = "examples/backends/vllm/deploy/disagg.yaml"
self.output_dir = "/tmp/test_profiling_results"
self.namespace = "test-namespace"
self.model = ""
......@@ -82,7 +82,7 @@ class TestProfileSLADryRun:
class Args:
def __init__(self):
self.backend = "sglang"
self.config = "components/backends/sglang/deploy/disagg.yaml"
self.config = "examples/backends/sglang/deploy/disagg.yaml"
self.output_dir = "/tmp/test_profiling_results"
self.namespace = "test-namespace"
self.model = ""
......@@ -132,7 +132,7 @@ class TestProfileSLADryRun:
class Args:
def __init__(self):
self.backend = "trtllm"
self.config = "components/backends/trtllm/deploy/disagg.yaml"
self.config = "examples/backends/trtllm/deploy/disagg.yaml"
self.output_dir = "/tmp/test_profiling_results"
self.namespace = "test-namespace"
self.model = ""
......
......@@ -34,7 +34,7 @@ class SGLangConfig(EngineConfig):
sglang_dir = os.environ.get("SGLANG_DIR") or os.path.join(
WORKSPACE_DIR, "components/backends/sglang"
WORKSPACE_DIR, "examples/backends/sglang"
)
sglang_configs = {
......
......@@ -30,7 +30,7 @@ class TRTLLMConfig(EngineConfig):
trtllm_dir = os.environ.get("TRTLLM_DIR") or os.path.join(
WORKSPACE_DIR, "components/backends/trtllm"
WORKSPACE_DIR, "examples/backends/trtllm"
)
# trtllm test configurations
......
......@@ -31,7 +31,7 @@ class VLLMConfig(EngineConfig):
vllm_dir = os.environ.get("VLLM_DIR") or os.path.join(
WORKSPACE_DIR, "components/backends/vllm"
WORKSPACE_DIR, "examples/backends/vllm"
)
# vLLM test configurations
......
......@@ -881,7 +881,7 @@ async def main():
workspace_dir = get_workspace_dir()
deployment_spec = DeploymentSpec(
os.path.join(workspace_dir, "components/backends/vllm/deploy/agg.yaml")
os.path.join(workspace_dir, "examples/backends/vllm/deploy/agg.yaml")
)
deployment_spec.disable_grove()
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment