feat: support vllm in controller #635
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
zhuangqh
force-pushed
the
controller-support-vllm
branch
from
936993c
to
1fcd0b1
Compare
zhuangqh
commented
Oct 28, 2024
docker/presets/models/tfs/Dockerfile
Outdated
| @@ -5,31 +5,39 @@ ARG MODEL_TYPE | |||
| ARG VERSION | |||
There was a problem hiding this comment.
.
├── chat_templates
│ ├── alpaca.jinja
│ ├── amberchat.jinja
│ ├── chatml.jinja
│ ├── chatqa.jinja
│ ├── falcon-instruct.jinja
│ ├── gemma-it.jinja
│ ├── llama-2-chat.jinja
│ ├── llama-3-instruct.jinja
│ ├── mistral-instruct.jinja
│ ├── openchat-3.5.jinja
│ ├── phi-3-small.jinja
│ ├── phi-3.jinja
│ ├── saiga.jinja
│ ├── solar-instruct.jinja
│ ├── vicuna.jinja
│ └── zephyr.jinja
├── tfs
│ ├── cli.py
│ ├── dataset.py
│ ├── fine_tuning.py
│ ├── inference-requirements.txt
│ ├── inference_api.py
│ ├── metrics_server.py
│ ├── parser.py
│ ├── tuning-requirements.txt
│ └── weights -> /workspace/weights
├── version.txt
├── vllm
│ ├── inference-requirements.txt
│ ├── inference_api.py
│ └── weights -> /workspace/weights
└── weights
zhuangqh
commented
Oct 28, 2024
| ModelRunParams map[string]string // Parameters for running the model training/inference. | ||
| } | ||
|
|
||
| func (p *PresetParam) DeepCopy() *PresetParam { |
There was a problem hiding this comment.
we may update some params according to the node counts. Thus, we must deepcopy it at first.
zhuangqh
force-pushed
the
controller-support-vllm
branch
from
3dbfdb6
to
3b52cc4
Compare
- set vllm as the default runtime Signed-off-by: jerryzhuang <[email protected]>
zhuangqh
force-pushed
the
controller-support-vllm
branch
from
3b52cc4
to
8244ebc
Compare
Signed-off-by: jerryzhuang <[email protected]>
| TorchRunRdzvParams map[string]string // Optional rendezvous parameters for distributed training/inference using torchrun (elastic). | ||
| BaseCommand string // The initial command (e.g., 'torchrun', 'accelerate launch') used in the command line. | ||
| ModelRunParams map[string]string // Parameters for running the model training/inference. | ||
| Tag string // The model image tag |
There was a problem hiding this comment.
does this tag field get used
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Reason for Change:
Requirements