pre-commit formatting fixes

Command had accidentally been moved out of if-else block.

src/axolotl/monkeypatch/llama_attn_hijack_xformers.py

@@ -7,6 +7,7 @@ import math
 from typing import Optional, Tuple
 
 import torch
+import torch.nn.functional as F
 import transformers.models.llama.modeling_llama
 from torch import nn
 
@@ -38,21 +39,48 @@ def xformers_forward(
     # pylint: disable=duplicate-code
     bsz, q_len, _ = hidden_states.size()
 
-    query_states = (
-        self.q_proj(hidden_states)
-        .view(bsz, q_len, self.num_heads, self.head_dim)
-        .transpose(1, 2)
-    )
-    key_states = (
-        self.k_proj(hidden_states)
-        .view(bsz, q_len, self.num_heads, self.head_dim)
-        .transpose(1, 2)
-    )
-    value_states = (
-        self.v_proj(hidden_states)
-        .view(bsz, q_len, self.num_heads, self.head_dim)
-        .transpose(1, 2)
+    if not hasattr(self, "pretraining_tp"):
+        self.pretraining_tp = 1
+
+    if self.pretraining_tp > 1:
+        key_value_slicing = (
+            self.num_key_value_heads * self.head_dim
+        ) // self.pretraining_tp
+        query_slices = self.q_proj.weight.split(
+            (self.num_heads * self.head_dim) // self.pretraining_tp, dim=0
         )
+        key_slices = self.k_proj.weight.split(key_value_slicing, dim=0)
+        value_slices = self.v_proj.weight.split(key_value_slicing, dim=0)
+
+        query_states = [
+            F.linear(hidden_states, query_slices[i]) for i in range(self.pretraining_tp)
+        ]
+        query_states = torch.cat(query_states, dim=-1)
+
+        key_states = [
+            F.linear(hidden_states, key_slices[i]) for i in range(self.pretraining_tp)
+        ]
+        key_states = torch.cat(key_states, dim=-1)
+
+        value_states = [
+            F.linear(hidden_states, value_slices[i]) for i in range(self.pretraining_tp)
+        ]
+        value_states = torch.cat(value_states, dim=-1)
+
+    else:
+        query_states = self.q_proj(hidden_states)
+        key_states = self.k_proj(hidden_states)
+        value_states = self.v_proj(hidden_states)
+
+    query_states = query_states.view(
+        bsz, q_len, self.num_heads, self.head_dim
+    ).transpose(1, 2)
+    key_states = key_states.view(
+        bsz, q_len, self.num_key_value_heads, self.head_dim
+    ).transpose(1, 2)
+    value_states = value_states.view(
+        bsz, q_len, self.num_key_value_heads, self.head_dim
+    ).transpose(1, 2)
 
     kv_seq_len = key_states.shape[-2]
     if past_key_value is not None:
@@ -73,6 +101,14 @@ def xformers_forward(
 
     past_key_value = (key_states, value_states) if use_cache else None
 
+    # repeat k/v heads if n_kv_heads < n_heads
+    key_states = transformers.models.llama.modeling_llama.repeat_kv(
+        key_states, self.num_key_value_groups
+    )
+    value_states = transformers.models.llama.modeling_llama.repeat_kv(
+        value_states, self.num_key_value_groups
+    )
+
     # We only apply xformers optimizations if we don't need to output the whole attention matrix
     if not output_attentions:
         query_states = query_states.transpose(1, 2)
@@ -128,10 +164,23 @@ def xformers_forward(
                 f" {attn_output.size()}"
             )
 
-        attn_output = attn_output.transpose(1, 2)
+        attn_output = attn_output.transpose(1, 2).contiguous()
+        # end x-formers vs. not x-formers if-else block
 
     attn_output = attn_output.reshape(bsz, q_len, self.hidden_size)
+
+    if self.pretraining_tp > 1:
+        attn_output = attn_output.split(self.hidden_size // self.pretraining_tp, dim=2)
+        o_proj_slices = self.o_proj.weight.split(
+            self.hidden_size // self.pretraining_tp, dim=1
+        )
+        attn_output = sum(
+            F.linear(attn_output[i], o_proj_slices[i])
+            for i in range(self.pretraining_tp)
+        )
+    else:
         attn_output = self.o_proj(attn_output)
+
     return attn_output, attn_weights, past_key_value