Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[Bugfix] Fix Phi3.5 mini and MoE LoRA inference #8571

Merged
merged 4 commits into from
Sep 20, 2024
Merged

[Bugfix] Fix Phi3.5 mini and MoE LoRA inference #8571

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
524e1d3
added moe lora modules
garg-amit Sep 14, 2024
e927435
Merge branch 'main' of https://github.com/garg-amit/vllm into fix_moe…
garg-amit Sep 17, 2024
ba25f71
created a new class for Phi3 models; Fixed LoRA ft inference
garg-amit Sep 17, 2024
1fb9c5c
address comments
garg-amit Sep 19, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion vllm/model_executor/models/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,7 +50,7 @@
"OrionForCausalLM": ("orion", "OrionForCausalLM"),
"PersimmonForCausalLM": ("persimmon", "PersimmonForCausalLM"),
"PhiForCausalLM": ("phi", "PhiForCausalLM"),
"Phi3ForCausalLM": ("llama", "LlamaForCausalLM"),
"Phi3ForCausalLM": ("phi3", "Phi3ForCausalLM"),
"PhiMoEForCausalLM": ("phimoe", "PhiMoEForCausalLM"),
"Qwen2ForCausalLM": ("qwen2", "Qwen2ForCausalLM"),
"Qwen2MoeForCausalLM": ("qwen2_moe", "Qwen2MoeForCausalLM"),
Expand Down
17 changes: 17 additions & 0 deletions vllm/model_executor/models/phi3.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,17 @@
# coding=utf-8
# Adapted from llama.py
"""Inference-only Phi3 model code inherit from Llama.py"""

from vllm.model_executor.models.llama import LlamaForCausalLM


class Phi3ForCausalLM(LlamaForCausalLM):

packed_modules_mapping = {
"qkv_proj": [
"qkv_proj",
],
"gate_up_proj": [
"gate_up_proj",
],
}
4 changes: 4 additions & 0 deletions vllm/model_executor/models/phimoe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -491,6 +491,10 @@ class PhiMoEForCausalLM(nn.Module, SupportsLoRA):
"o_proj",
"embed_tokens",
"lm_head",
"w1",
"w2",
"w3",
"gate",
]
embedding_modules = {
"embed_tokens": "input_embeddings",
Expand Down
Loading