Merge pull request oobabooga#7352 from oobabooga/dev

Merge dev branch

Author: oobabooga

requirements/full/requirements.txt

@@ -22,13 +22,13 @@ python-docx==1.1.2
 pyyaml
 requests
 rich
-safetensors==0.6.*
+safetensors==0.7.*
 scipy
 sentencepiece
 tensorboard
 torchao==0.14.*
 transformers==4.57.*
-triton-windows==3.5.1.post21; platform_system == "Windows"
+triton-windows==3.5.1.post22; platform_system == "Windows"
 tqdm
 wandb
 
@@ -42,10 +42,10 @@ sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.66.0/llama_cpp_binaries-0.66.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.66.0/llama_cpp_binaries-0.66.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/turboderp-org/exllamav3/releases/download/v0.0.17/exllamav3-0.0.17+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/turboderp-org/exllamav3/releases/download/v0.0.17/exllamav3-0.0.17+cu128.torch2.7.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/turboderp-org/exllamav3/releases/download/v0.0.18/exllamav3-0.0.18+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/turboderp-org/exllamav3/releases/download/v0.0.18/exllamav3-0.0.18+cu128.torch2.7.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu128.torch2.7.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64"

requirements/full/requirements_amd.txt

@@ -20,13 +20,13 @@ python-docx==1.1.2
 pyyaml
 requests
 rich
-safetensors==0.6.*
+safetensors==0.7.*
 scipy
 sentencepiece
 tensorboard
 torchao==0.14.*
 transformers==4.57.*
-triton-windows==3.5.1.post21; platform_system == "Windows"
+triton-windows==3.5.1.post22; platform_system == "Windows"
 tqdm
 wandb
 
@@ -40,7 +40,7 @@ sse-starlette==1.6.5
 tiktoken
 
 # AMD wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.66.0/llama_cpp_binaries-0.66.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.66.0/llama_cpp_binaries-0.66.0+rocm6.4.4-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+rocm6.4.4-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+rocm6.2.4.torch2.6.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"

requirements/full/requirements_amd_noavx2.txt

@@ -20,13 +20,13 @@ python-docx==1.1.2
 pyyaml
 requests
 rich
-safetensors==0.6.*
+safetensors==0.7.*
 scipy
 sentencepiece
 tensorboard
 torchao==0.14.*
 transformers==4.57.*
-triton-windows==3.5.1.post21; platform_system == "Windows"
+triton-windows==3.5.1.post22; platform_system == "Windows"
 tqdm
 wandb
 
@@ -40,7 +40,7 @@ sse-starlette==1.6.5
 tiktoken
 
 # AMD wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.66.0/llama_cpp_binaries-0.66.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.66.0/llama_cpp_binaries-0.66.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+rocm6.2.4.torch2.6.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"

requirements/full/requirements_apple_intel.txt

@@ -20,13 +20,13 @@ python-docx==1.1.2
 pyyaml
 requests
 rich
-safetensors==0.6.*
+safetensors==0.7.*
 scipy
 sentencepiece
 tensorboard
 torchao==0.14.*
 transformers==4.57.*
-triton-windows==3.5.1.post21; platform_system == "Windows"
+triton-windows==3.5.1.post22; platform_system == "Windows"
 tqdm
 wandb
 
@@ -40,5 +40,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.66.0/llama_cpp_binaries-0.66.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.66.0/llama_cpp_binaries-0.66.0-py3-none-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0-py3-none-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"

requirements/full/requirements_apple_silicon.txt

@@ -20,13 +20,13 @@ python-docx==1.1.2
 pyyaml
 requests
 rich
-safetensors==0.6.*
+safetensors==0.7.*
 scipy
 sentencepiece
 tensorboard
 torchao==0.14.*
 transformers==4.57.*
-triton-windows==3.5.1.post21; platform_system == "Windows"
+triton-windows==3.5.1.post22; platform_system == "Windows"
 tqdm
 wandb
 
@@ -40,5 +40,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.66.0/llama_cpp_binaries-0.66.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.66.0/llama_cpp_binaries-0.66.0-py3-none-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0-py3-none-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"

requirements/full/requirements_cpu_only.txt

@@ -20,13 +20,13 @@ python-docx==1.1.2
 pyyaml
 requests
 rich
-safetensors==0.6.*
+safetensors==0.7.*
 scipy
 sentencepiece
 tensorboard
 torchao==0.14.*
 transformers==4.57.*
-triton-windows==3.5.1.post21; platform_system == "Windows"
+triton-windows==3.5.1.post22; platform_system == "Windows"
 tqdm
 wandb
 
@@ -40,5 +40,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # llama.cpp (CPU only, AVX2)
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.66.0/llama_cpp_binaries-0.66.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.66.0/llama_cpp_binaries-0.66.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows"

requirements/full/requirements_cpu_only_noavx2.txt

@@ -20,13 +20,13 @@ python-docx==1.1.2
 pyyaml
 requests
 rich
-safetensors==0.6.*
+safetensors==0.7.*
 scipy
 sentencepiece
 tensorboard
 torchao==0.14.*
 transformers==4.57.*
-triton-windows==3.5.1.post21; platform_system == "Windows"
+triton-windows==3.5.1.post22; platform_system == "Windows"
 tqdm
 wandb
 
@@ -40,5 +40,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # llama.cpp (CPU only, no AVX2)
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.66.0/llama_cpp_binaries-0.66.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.66.0/llama_cpp_binaries-0.66.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows"

requirements/full/requirements_noavx2.txt

@@ -22,13 +22,13 @@ python-docx==1.1.2
 pyyaml
 requests
 rich
-safetensors==0.6.*
+safetensors==0.7.*
 scipy
 sentencepiece
 tensorboard
 torchao==0.14.*
 transformers==4.57.*
-triton-windows==3.5.1.post21; platform_system == "Windows"
+triton-windows==3.5.1.post22; platform_system == "Windows"
 tqdm
 wandb
 
@@ -42,10 +42,10 @@ sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.66.0/llama_cpp_binaries-0.66.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.66.0/llama_cpp_binaries-0.66.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/turboderp-org/exllamav3/releases/download/v0.0.17/exllamav3-0.0.17+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/turboderp-org/exllamav3/releases/download/v0.0.17/exllamav3-0.0.17+cu128.torch2.7.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/turboderp-org/exllamav3/releases/download/v0.0.18/exllamav3-0.0.18+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/turboderp-org/exllamav3/releases/download/v0.0.18/exllamav3-0.0.18+cu128.torch2.7.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu128.torch2.7.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64"

requirements/full/requirements_nowheels.txt

@@ -20,13 +20,13 @@ python-docx==1.1.2
 pyyaml
 requests
 rich
-safetensors==0.6.*
+safetensors==0.7.*
 scipy
 sentencepiece
 tensorboard
 torchao==0.14.*
 transformers==4.57.*
-triton-windows==3.5.1.post21; platform_system == "Windows"
+triton-windows==3.5.1.post22; platform_system == "Windows"
 tqdm
 wandb
 

requirements/portable/requirements.txt

@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.66.0/llama_cpp_binaries-0.66.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.66.0/llama_cpp_binaries-0.66.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"