Skip to content

Comments

feat(full_llama_optimized):implemented#3

Closed
Kenaz123 wants to merge 1 commit intoquest-llama-optimizedfrom
llama-optimized
Closed

feat(full_llama_optimized):implemented#3
Kenaz123 wants to merge 1 commit intoquest-llama-optimizedfrom
llama-optimized

Conversation

@Kenaz123
Copy link
Collaborator

  1. code logic in full-llama-optimized driven code in e2e
  2. disable GQA in full_llama by copy and store the same kv_states in forwarding process

@rijuyuezhu
Copy link
Collaborator

Covered by #4

@rijuyuezhu rijuyuezhu closed this Jan 27, 2025
@DerekHJH DerekHJH deleted the llama-optimized branch February 10, 2025 02:45
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants