From 7e1c6a62e26abfdc8bb82bacfcba21b1364a8032 Mon Sep 17 00:00:00 2001
From: Daniel Han <danielhanchen@gmail.com>
Date: Wed, 3 Apr 2024 05:38:31 +1100
Subject: [PATCH] Nightly (#299)

* Update llama.py

* Update llama.py

* Update gemma.py

* correct_dtype

* Update gemma.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Chat Templates

* Update README.md

* Update README.md

* Update llama.py

* DoRA

* Update _utils.py

* Update chat_templates.py

* Update llama.py

* Hotfix - fix DoRA, Gemma prompt template (#202) (#203)

* Update save.py

* saving

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* Update __init__.py

* Update save.py

* Update save.py

* Update save.py

* save

* trainer

* spaces

* original

* Gemma

* Update pyproject.toml

* Update mapper.py

* Update fast_lora.py

* FastGemmaModel

* model_type

* Update llama.py

* Update llama.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update llama.py

* Update llama.py

* Update fast_lora.py

* Update llama.py

* Update llama.py

* Update cross_entropy_loss.py

* Update llama.py

* Update llama.py

* gemma

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update fast_lora.py

* Update fast_lora.py

* Fast CE Loss

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* CE

* Update llama.py

* Update llama.py

* Update cross_entropy_loss.py

* Update geglu.py

* Update cross_entropy_loss.py

* revert

* Update llama.py

* Update llama.py

* norm

* Update gemma.py

* Update gemma.py

* position_ids

* Update gemma.py

* Update gemma.py

* pos

* Update llama.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update cross_entropy_loss.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update llama.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update llama.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* revert

* revert

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update llama.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update cross_entropy_loss.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* rope

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* llama

* Update llama.py

* gemma

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update save.py

* RoPE

* Update llama.py

* Update llama.py

* Update llama.py

* Update gemma.py

* correct_dtype

* Update gemma.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Chat Templates

* Update README.md

* Update README.md

* Update llama.py

* DoRA

* Update _utils.py

* Update chat_templates.py

* Update pyproject.toml

* Small fixes

* Update pyproject.toml

* Approx gelu

* Update geglu.py

* Approx gelu

* Update llama.py

* Update __init__.py

* Update __init__.py

* Update _utils.py

* Update geglu.py

* Update gemma.py

* Update rms_layernorm.py

* Update rms_layernorm.py

* Update rms_layernorm.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Fix Gemma merging

* Update rms_layernorm.py

* Update gemma.py

* Update pyproject.toml

* Layernorms

* Gemma precision

* Update gemma.py

* sqrt

* Update gemma.py

* Update save.py

* RoPE and Gemma precision

* Update rms_layernorm.py

* Fix warning

* Update chat_templates.py

* Update chat_templates.py

* Update save.py

* Update save.py

* Update save.py

* Update chat_templates.py

* Update llama.py

* model_name

* Update loader.py

* Tokenizer overwritten

* Update llama.py

* Update llama.py

* Update llama.py

* Update save.py

* Accuracy

* Revert

* Update save.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update chat_templates.py

* Update save.py

* Update save.py

* Update llama.py

* Update llama.py

* Account for DoRA

* Update llama.py

* Update save.py

* GGUF incorrect

* Update save.py

* Update pyproject.toml

* kaggle new

* Update pyproject.toml

* Update pyproject.toml

* upcasting

* Fix Colab

* Update pyproject.toml

* Update pyproject.toml

* Update pyproject.toml

* Update pyproject.toml

* Update pyproject.toml

* Update pyproject.toml

* Update pyproject.toml

* Update pyproject.toml

* Update chat_templates.py

* Update chat_templates.py

* Update chat_templates.py

* Update chat_templates.py

* Update chat_templates.py

* Update pyproject.toml

* Update pyproject.toml

* Update pyproject.toml

* Update rope_embedding.py

* Update rope_embedding.py

* Fix bugs

* Update fast_lora.py

* Update fast_lora.py

* Update README.md

* Update README.md

* GGUF

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* Update README.md

* Update README.md

* Bugs

* Update fast_lora.py

* Update pyproject.toml

* Update fast_lora.py

* Update __init__.py

* Update fast_lora.py

* dtype

* Update llama.py

* Update llama.py

* Update llama.py

* dtype

* Update mistral.py

* trust_remote_code

* lm_head

* Update llama.py

* save_pretrained_settings

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* state_dict

* Update save.py

* whoami

* Update llama.py

* Update save.py

* Update llama.py

* Patch tokenizer

* Update chat_templates.py

* Heal tokenizers

* Update chat_templates.py

* Update mapper.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update chat_templates.py

* tokenizer patching

* patch_tokenizer

* Update chat_templates.py

* Update tokenizer_utils.py

* Update chat_templates.py

* Update chat_templates.py

* Update chat_templates.py

* Update tokenizer_utils.py

* Edit

* Update mistral.py

* Update mistral.py

* Stats

* Update mistral.py

* attention_mask

* Update llama.py

* Update llama.py

* batch

* Temp fix batch inference

* Update llama.py

* Update gemma.py

* Fix inference

* swiglu

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update mistral.py

* Update llama.py

* fast inference

* model

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update utils.py

* Update llama.py

* Update utils.py

* inference

* Update llama.py

* Update llama.py

* Update llama.py

* overhead

* Update llama.py

* Update llama.py

* compile

* Update gemma.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update utils.py

* Update utils.py

* lora mamtul
---
 unsloth/kernels/__init__.py  |  2 +-
 unsloth/kernels/fast_lora.py | 27 +--------------------------
 unsloth/kernels/utils.py     | 29 +++++++++++++++++++++++++++--
 3 files changed, 29 insertions(+), 29 deletions(-)

diff --git a/unsloth/kernels/__init__.py b/unsloth/kernels/__init__.py
index 8ff255e4a4..cb04377b1a 100644
--- a/unsloth/kernels/__init__.py
+++ b/unsloth/kernels/__init__.py
@@ -30,4 +30,4 @@ from .fast_lora import (
 	apply_lora_qkv,
 	apply_lora_o,
 )
-from .utils import fast_dequantize, fast_gemv, QUANT_STATE, fast_linear_forward
+from .utils import fast_dequantize, fast_gemv, QUANT_STATE, fast_linear_forward, matmul_lora
diff --git a/unsloth/kernels/fast_lora.py b/unsloth/kernels/fast_lora.py
index 6568bba681..aba44f0214 100644
--- a/unsloth/kernels/fast_lora.py
+++ b/unsloth/kernels/fast_lora.py
@@ -13,32 +13,7 @@
 # limitations under the License.
 
 import torch
-from .utils import fast_dequantize, QUANT_STATE, get_lora_parameters
-
-
-def matmul_lora(X, W, W_quant, A, B, s, out = None):
-    dtype = X.dtype
-    W = fast_dequantize(W.t(), W_quant)
-
-    if X.dim() == 3:
-        batch, seq_len, d = X.shape
-        X = X.view(-1, X.shape[-1])
-        reshape = True
-    else:
-        reshape = False
-    pass
-
-    out = torch.matmul(X, W, out = out)
-    if W_quant is not None: del W
-
-    if A is not None:
-        # LoRA is enabled
-        A, B = A.t(), B.t()
-        out += (X @ A.to(dtype)) @ (s * B.to(dtype))
-    pass
-    
-    return out.view(batch, seq_len, -1) if reshape else out
-pass
+from .utils import fast_dequantize, QUANT_STATE, get_lora_parameters, matmul_lora
 
 
 class LoRA_MLP(torch.autograd.Function):
diff --git a/unsloth/kernels/utils.py b/unsloth/kernels/utils.py
index 76f0a9854a..1f2085df5a 100644
--- a/unsloth/kernels/utils.py
+++ b/unsloth/kernels/utils.py
@@ -182,8 +182,8 @@ pass
 def fast_linear_forward(proj, X, temp_lora = None, out = None):
 
     W, W_quant, lora_A, lora_B, lora_S = get_lora_parameters(proj)
-
     bsz, q_len, in_dim = X.shape
+    if q_len != 1: return matmul_lora(X, W, W_quant, lora_A, lora_B, lora_S)
 
     if W_quant is None:
         out = torch.matmul(X, W.t(), out = out)
@@ -203,7 +203,7 @@ def fast_linear_forward(proj, X, temp_lora = None, out = None):
             lora_A._fast_lora = lora_A.to(dtype)
             lora_B._fast_lora = lora_B.to(dtype)
         pass
-
+        
         if bsz == 1:
             out = out.view(out_dim)
             temp_lora = torch.mv(lora_A._fast_lora, X.ravel(), out = temp_lora)
@@ -218,3 +218,28 @@ def fast_linear_forward(proj, X, temp_lora = None, out = None):
 
     return out
 pass
+
+
+def matmul_lora(X, W, W_quant, A, B, s, out = None):
+    dtype = X.dtype
+    W = fast_dequantize(W.t(), W_quant)
+
+    if X.dim() == 3:
+        batch, seq_len, d = X.shape
+        X = X.view(-1, X.shape[-1])
+        reshape = True
+    else:
+        reshape = False
+    pass
+
+    out = torch.matmul(X, W, out = out)
+    if W_quant is not None: del W
+
+    if A is not None:
+        # LoRA is enabled
+        A, B = A.t(), B.t()
+        out += (X @ A.to(dtype)) @ (s * B.to(dtype))
+    pass
+    
+    return out.view(batch, seq_len, -1) if reshape else out
+pass