Alex Reichenbach
Alex Reichenbach
Also bumping on this. Would love this feature to be added.
[a670aae](https://github.com/StructifyAI/llm/commit/a670aae2e919de7053a6188ee91c19b784baa77a)
I'm also running into this.
I agree this should be merged, but for others who find this, I solved with this: ``` steps: - name: "gcr.io/cloud-builders/docker" script: | apt-get update && apt-get install -y git-lfs...
Has there been any recent movement on this? I'm hoping to do some constrained JSON generation using this crate. Is this the right package to push for this or should...
Bump on this. We're running into it too. Would appreciate guidance.
Any update on this?
Any updates on this thread?
Haven't gotten a response from them yet, but as a quick and dirty workaround for anyone who hits this thread: ``` from vllm.model_executor.layers.vocab_parallel_embedding import VocabParallelEmbedding def init_wrapper( self, num_embeddings: int,...