add internlm model #528
Merged
add internlm model #528
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
Add support for LLaMA-2 (vllm-project#505)
zhuohan123
reviewed
Jul 25, 2023
There was a problem hiding this comment.
Thank you for your contribution! Can you add your models to EADME.md and docs/source/models/supported_models.rst? Specifically, have you made sure that your implementation matches the official implementation? For example, does the greedy sampling results from this PR matches the official implementation?
zhuohan123
approved these changes
Aug 8, 2023
|
Hi, why I still got: vllm version: 0.1.3 script: |
hongxiayang
pushed a commit
to hongxiayang/vllm
that referenced
this pull request
Feb 13, 2024
rickyyx
pushed a commit
to rickyyx/vllm
that referenced
this pull request
Oct 7, 2024
NOTE: This includes a couple importing order changes. It is because I made vllm.anyscale pakcages to go to the bottom to avoid merge conflict. Allow to build via pip install -e . Basic integration with an env var ANYSCALE_USE_SCRATCH=1 Working with Llama 7B Basic testing Batch working (but scratch only allows small number of batch now. And scratch doesn't have efficient batching yet) It is working with both scratch sampler and vllm sampler Sessions are cleaned based on LRU cache. It will be fixed in a couple weeks. support prompt logprob and some sampler features (except beam search) async execution like torch kernels llama 3 + llama 2 works Do input config validation more thorough testing Future TODO preemption not working (future work) It currently doesn't use kv cache allocated from vllm (not a strict requirement). The PR needs cleanup before merging.
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.
No description provided.