phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-04 04:42:16 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

several fixes

Browse source
This commit is contained in:
Ashwin Bharambe 2025-04-07 10:31:20 -07:00
parent e2e2820c9a
commit 53a8086e37
60 changed files with 1006 additions and 1078 deletions
Download patch file Download diff file Expand all files Collapse all files

20
llama_stack/models/llama/llama3/model.py
View file

@ -4,16 +4,6 @@
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
#
# This source code is licensed under the terms described in the LICENSE file in
# top-level folder for each specific model found within the models/ directory at
# the top-level of this source tree.
# Copyright (c) Meta Platforms, Inc. and affiliates.
# This software may be used and distributed in accordance with the terms of the Llama 3 Community License Agreement.
import math
from typing import Optional, Tuple
@ -29,6 +19,10 @@ from torch import nn
from .args import ModelArgs
# **NOTE**: This code is not runnable without installing `torch` and `fairscale`
# dependencies. These dependencies are not part of the default dependencies
# (requirements.txt) of the `llama-models` package.
class RMSNorm(torch.nn.Module):
def __init__(self, dim: int, eps: float = 1e-6):
@ -111,9 +105,9 @@ class Attention(nn.Module):
def __init__(self, args: ModelArgs):
super().__init__()
self.n_kv_heads = args.n_heads if args.n_kv_heads is None else args.n_kv_heads
model_parallel_size = fs_init.get_model_parallel_world_size()
self.n_local_heads = args.n_heads // model_parallel_size
self.n_local_kv_heads = self.n_kv_heads // model_parallel_size
world_size = fs_init.get_model_parallel_world_size()
self.n_local_heads = args.n_heads // world_size
self.n_local_kv_heads = self.n_kv_heads // world_size
self.n_rep = self.n_local_heads // self.n_local_kv_heads
self.head_dim = args.dim // args.n_heads