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Outdated suggestions cannot be applied.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.
Add ChatGLM Model loading. Code adapted from vllm main.
Notable Changes:
model_config.get_num_kv_heads()
and.get_total_num_kv_heads()
ported from vllm to correctly caculate kv heads from model config json. Found that chatglm with sglang main code retrieved wrong kv heads from config causing kv cache to contain the wrong shape.EntryClassRemapping
property added to model entry definition to help with future compat. Chatglm hasChatGLMModel
set inconfig.json
when model loader needsChatGLMForCausalLM
.Remapping code:
Usage:
TESTS:
get_num_kv_heads