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Outdated suggestions cannot be applied.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.
Blocked by #598
Add Qwen2 MoE support to SGLang. Implementation is adopted from the current vLLM implementation.
I've tested this patch on my local environment with 8 * A800, and everything works gracefully.
The configurations I've tested so far are
CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python -m sglang.launch_server --model-path ~/Qwen2-57B-A14B-Instruct/ --port 30000 --mem-fraction-static 0.9 --tp-size 8
CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python -m sglang.launch_server --model-path ~/Qwen2-57B-A14B-Instruct/ --port 30000 --mem-fraction-static 0.9 --tp-size 4 --dp-size 2
CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python -m sglang.launch_server --model-path ~/Qwen2-57B-A14B-Instruct/ --port 30000 --mem-fraction-static 0.9 --tp-size 2 --dp-size 4