oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-03-04 20:53:50 +01:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge pull request #7231 from oobabooga/dev

Browse source 
Merge dev branch
This commit is contained in:
oobabooga 2025-09-21 01:18:56 -03:00 committed by GitHub
parent d3a7710c62 8c9df34696
commit 042b828c73
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
22 changed files with 106 additions and 97 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

63
js/main.js
View file

@ -249,45 +249,46 @@ function doSyntaxHighlighting() {
if (messageBodies.length > 0) {
observer.disconnect();
let hasSeenVisible = false;
try {
let hasSeenVisible = false;
// Go from last message to first
for (let i = messageBodies.length - 1; i >= 0; i--) {
const messageBody = messageBodies[i];
// Go from last message to first
for (let i = messageBodies.length - 1; i >= 0; i--) {
const messageBody = messageBodies[i];
if (isElementVisibleOnScreen(messageBody)) {
hasSeenVisible = true;
if (isElementVisibleOnScreen(messageBody)) {
hasSeenVisible = true;
// Handle both code and math in a single pass through each message
const codeBlocks = messageBody.querySelectorAll("pre code:not([data-highlighted])");
codeBlocks.forEach((codeBlock) => {
hljs.highlightElement(codeBlock);
codeBlock.setAttribute("data-highlighted", "true");
codeBlock.classList.add("pretty_scrollbar");
});
// Handle both code and math in a single pass through each message
const codeBlocks = messageBody.querySelectorAll("pre code:not([data-highlighted])");
codeBlocks.forEach((codeBlock) => {
hljs.highlightElement(codeBlock);
codeBlock.setAttribute("data-highlighted", "true");
codeBlock.classList.add("pretty_scrollbar");
});
// Only render math in visible elements
const mathContainers = messageBody.querySelectorAll("p, span, li, td, th, h1, h2, h3, h4, h5, h6, blockquote, figcaption, caption, dd, dt");
mathContainers.forEach(container => {
if (isElementVisibleOnScreen(container)) {
renderMathInElement(container, {
delimiters: [
{ left: "$$", right: "$$", display: true },
{ left: "$", right: "$", display: false },
{ left: "\\(", right: "\\)", display: false },
{ left: "\\[", right: "\\]", display: true },
],
});
}
});
} else if (hasSeenVisible) {
// Only render math in visible elements
const mathContainers = messageBody.querySelectorAll("p, span, li, td, th, h1, h2, h3, h4, h5, h6, blockquote, figcaption, caption, dd, dt");
mathContainers.forEach(container => {
if (isElementVisibleOnScreen(container)) {
renderMathInElement(container, {
delimiters: [
{ left: "$$", right: "$$", display: true },
{ left: "\\(", right: "\\)", display: false },
{ left: "\\[", right: "\\]", display: true },
],
});
}
});
} else if (hasSeenVisible) {
// We've seen visible messages but this one is not visible
// Since we're going from last to first, we can break
break;
break;
}
}
} finally {
observer.observe(targetElement, config);
}
observer.observe(targetElement, config);
}
}

4
modules/exllamav2_hf.py
View file

@ -35,7 +35,9 @@ except Exception:
class Exllamav2HF(PreTrainedModel, GenerationMixin):
def __init__(self, config: ExLlamaV2Config):
super().__init__(PretrainedConfig())
hf_config = PretrainedConfig.from_pretrained(config.model_dir)
super().__init__(hf_config)
self.ex_config = config
self.loras = None
self.generation_config = GenerationConfig()

3
modules/exllamav3.py
View file

@ -344,6 +344,9 @@ class Exllamav3Model:
try:
while self.generator.num_remaining_jobs():
if shared.stop_everything:
break
results = self.generator.iterate()
for result in results:
if "eos" in result and result["eos"]:

10
modules/exllamav3_hf.py
View file

@ -27,11 +27,13 @@ except Exception:
class Exllamav3HF(PreTrainedModel, GenerationMixin):
def __init__(self, model_dir):
super().__init__(PretrainedConfig())
self.generation_config = GenerationConfig()
hf_config = PretrainedConfig.from_pretrained(model_dir)
super().__init__(hf_config)
config = Config.from_directory(model_dir)
self.ex_model = Model.from_config(config)
exl3_config = Config.from_directory(model_dir)
self.generation_config = GenerationConfig()
self.ex_model = Model.from_config(exl3_config)
# Calculate the closest multiple of 256 at or above the chosen value
max_tokens = shared.args.ctx_size

1
modules/transformers_loader.py
View file

@ -137,6 +137,7 @@ def load_model_HF(model_name):
params = {
'low_cpu_mem_usage': True,
'attn_implementation': shared.args.attn_implementation,
'torch_dtype': torch.bfloat16 if shared.args.bf16 else torch.float16,
}
if shared.args.trust_remote_code:

10
requirements/full/requirements.txt
View file

@ -11,7 +11,7 @@ jinja2==3.1.6
markdown
numpy==2.2.*
pandas
peft==0.16.*
peft==0.17.*
Pillow>=9.5.0
psutil
pydantic==2.8.2
@ -20,11 +20,11 @@ python-docx==1.1.2
pyyaml
requests
rich
safetensors==0.5.*
safetensors==0.6.*
scipy
sentencepiece
tensorboard
transformers==4.55.*
transformers==4.56.*
triton-windows==3.3.1.post19; platform_system == "Windows"
tqdm
wandb
@ -35,8 +35,8 @@ sse-starlette==1.6.5
tiktoken
# CUDA wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.42.0/llama_cpp_binaries-0.42.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.42.0/llama_cpp_binaries-0.42.0+cu124-py3-none-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/v0.46.0/llama_cpp_binaries-0.46.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.46.0/llama_cpp_binaries-0.46.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/turboderp-org/exllamav3/releases/download/v0.0.6/exllamav3-0.0.6+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/v0.0.6/exllamav3-0.0.6+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"

10
requirements/full/requirements_amd.txt
View file

@ -10,7 +10,7 @@ jinja2==3.1.6
markdown
numpy==2.2.*
pandas
peft==0.16.*
peft==0.17.*
Pillow>=9.5.0
psutil
pydantic==2.8.2
@ -19,11 +19,11 @@ python-docx==1.1.2
pyyaml
requests
rich
safetensors==0.5.*
safetensors==0.6.*
scipy
sentencepiece
tensorboard
transformers==4.55.*
transformers==4.56.*
triton-windows==3.2.0.post19; platform_system == "Windows"
tqdm
wandb
@ -34,7 +34,7 @@ sse-starlette==1.6.5
tiktoken
# AMD wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.42.0/llama_cpp_binaries-0.42.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.42.0/llama_cpp_binaries-0.42.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.46.0/llama_cpp_binaries-0.46.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.46.0/llama_cpp_binaries-0.46.0+vulkan-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"

10
requirements/full/requirements_amd_noavx2.txt
View file

@ -10,7 +10,7 @@ jinja2==3.1.6
markdown
numpy==2.2.*
pandas
peft==0.16.*
peft==0.17.*
Pillow>=9.5.0
psutil
pydantic==2.8.2
@ -19,11 +19,11 @@ python-docx==1.1.2
pyyaml
requests
rich
safetensors==0.5.*
safetensors==0.6.*
scipy
sentencepiece
tensorboard
transformers==4.55.*
transformers==4.56.*
triton-windows==3.2.0.post19; platform_system == "Windows"
tqdm
wandb
@ -34,7 +34,7 @@ sse-starlette==1.6.5
tiktoken
# AMD wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.42.0/llama_cpp_binaries-0.42.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.42.0/llama_cpp_binaries-0.42.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.46.0/llama_cpp_binaries-0.46.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.46.0/llama_cpp_binaries-0.46.0+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"

10
requirements/full/requirements_apple_intel.txt
View file

@ -10,7 +10,7 @@ jinja2==3.1.6
markdown
numpy==2.2.*
pandas
peft==0.16.*
peft==0.17.*
Pillow>=9.5.0
psutil
pydantic==2.8.2
@ -19,11 +19,11 @@ python-docx==1.1.2
pyyaml
requests
rich
safetensors==0.5.*
safetensors==0.6.*
scipy
sentencepiece
tensorboard
transformers==4.55.*
transformers==4.56.*
triton-windows==3.2.0.post19; platform_system == "Windows"
tqdm
wandb
@ -34,7 +34,7 @@ sse-starlette==1.6.5
tiktoken
# Mac wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.42.0/llama_cpp_binaries-0.42.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and platform_release < "25.0.0" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.42.0/llama_cpp_binaries-0.42.0-py3-none-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.46.0/llama_cpp_binaries-0.46.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and platform_release < "25.0.0" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.46.0/llama_cpp_binaries-0.46.0-py3-none-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11"
https://github.com/oobabooga/exllamav3/releases/download/v0.0.6/exllamav3-0.0.6-py3-none-any.whl
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2-py3-none-any.whl

12
requirements/full/requirements_apple_silicon.txt
View file

@ -10,7 +10,7 @@ jinja2==3.1.6
markdown
numpy==2.2.*
pandas
peft==0.16.*
peft==0.17.*
Pillow>=9.5.0
psutil
pydantic==2.8.2
@ -19,11 +19,11 @@ python-docx==1.1.2
pyyaml
requests
rich
safetensors==0.5.*
safetensors==0.6.*
scipy
sentencepiece
tensorboard
transformers==4.55.*
transformers==4.56.*
triton-windows==3.2.0.post19; platform_system == "Windows"
tqdm
wandb
@ -34,8 +34,8 @@ sse-starlette==1.6.5
tiktoken
# Mac wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.42.0/llama_cpp_binaries-0.42.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and platform_release < "25.0.0" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.42.0/llama_cpp_binaries-0.42.0-py3-none-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.42.0/llama_cpp_binaries-0.42.0-py3-none-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.46.0/llama_cpp_binaries-0.46.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and platform_release < "25.0.0" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.46.0/llama_cpp_binaries-0.46.0-py3-none-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.46.0/llama_cpp_binaries-0.46.0-py3-none-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.11"
https://github.com/oobabooga/exllamav3/releases/download/v0.0.6/exllamav3-0.0.6-py3-none-any.whl
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2-py3-none-any.whl

10
requirements/full/requirements_cpu_only.txt
View file

@ -10,7 +10,7 @@ jinja2==3.1.6
markdown
numpy==2.2.*
pandas
peft==0.16.*
peft==0.17.*
Pillow>=9.5.0
psutil
pydantic==2.8.2
@ -19,11 +19,11 @@ python-docx==1.1.2
pyyaml
requests
rich
safetensors==0.5.*
safetensors==0.6.*
scipy
sentencepiece
tensorboard
transformers==4.55.*
transformers==4.56.*
triton-windows==3.2.0.post19; platform_system == "Windows"
tqdm
wandb
@ -34,5 +34,5 @@ sse-starlette==1.6.5
tiktoken
# llama.cpp (CPU only, AVX2)
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.42.0/llama_cpp_binaries-0.42.0+cpuavx2-py3-none-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/v0.42.0/llama_cpp_binaries-0.42.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.46.0/llama_cpp_binaries-0.46.0+cpuavx2-py3-none-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/v0.46.0/llama_cpp_binaries-0.46.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"

10
requirements/full/requirements_cpu_only_noavx2.txt
View file

@ -10,7 +10,7 @@ jinja2==3.1.6
markdown
numpy==2.2.*
pandas
peft==0.16.*
peft==0.17.*
Pillow>=9.5.0
psutil
pydantic==2.8.2
@ -19,11 +19,11 @@ python-docx==1.1.2
pyyaml
requests
rich
safetensors==0.5.*
safetensors==0.6.*
scipy
sentencepiece
tensorboard
transformers==4.55.*
transformers==4.56.*
triton-windows==3.2.0.post19; platform_system == "Windows"
tqdm
wandb
@ -34,5 +34,5 @@ sse-starlette==1.6.5
tiktoken
# llama.cpp (CPU only, no AVX2)
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.42.0/llama_cpp_binaries-0.42.0+cpuavx-py3-none-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/v0.42.0/llama_cpp_binaries-0.42.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.46.0/llama_cpp_binaries-0.46.0+cpuavx-py3-none-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/v0.46.0/llama_cpp_binaries-0.46.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"

10
requirements/full/requirements_noavx2.txt
View file

@ -11,7 +11,7 @@ jinja2==3.1.6
markdown
numpy==2.2.*
pandas
peft==0.16.*
peft==0.17.*
Pillow>=9.5.0
psutil
pydantic==2.8.2
@ -20,11 +20,11 @@ python-docx==1.1.2
pyyaml
requests
rich
safetensors==0.5.*
safetensors==0.6.*
scipy
sentencepiece
tensorboard
transformers==4.55.*
transformers==4.56.*
triton-windows==3.3.1.post19; platform_system == "Windows"
tqdm
wandb
@ -35,8 +35,8 @@ sse-starlette==1.6.5
tiktoken
# CUDA wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.42.0/llama_cpp_binaries-0.42.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.42.0/llama_cpp_binaries-0.42.0+cu124avx-py3-none-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/v0.46.0/llama_cpp_binaries-0.46.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.46.0/llama_cpp_binaries-0.46.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/turboderp-org/exllamav3/releases/download/v0.0.6/exllamav3-0.0.6+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/v0.0.6/exllamav3-0.0.6+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"

6
requirements/full/requirements_nowheels.txt
View file

@ -10,7 +10,7 @@ jinja2==3.1.6
markdown
numpy==2.2.*
pandas
peft==0.16.*
peft==0.17.*
Pillow>=9.5.0
psutil
pydantic==2.8.2
@ -19,11 +19,11 @@ python-docx==1.1.2
pyyaml
requests
rich
safetensors==0.5.*
safetensors==0.6.*
scipy
sentencepiece
tensorboard
transformers==4.55.*
transformers==4.56.*
triton-windows==3.2.0.post19; platform_system == "Windows"
tqdm
wandb

4
requirements/portable/requirements.txt
View file

@ -19,5 +19,5 @@ sse-starlette==1.6.5
tiktoken
# CUDA wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.42.0/llama_cpp_binaries-0.42.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.42.0/llama_cpp_binaries-0.42.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.46.0/llama_cpp_binaries-0.46.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.46.0/llama_cpp_binaries-0.46.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"

4
requirements/portable/requirements_apple_intel.txt
View file

@ -19,5 +19,5 @@ sse-starlette==1.6.5
tiktoken
# Mac wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.42.0/llama_cpp_binaries-0.42.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and platform_release < "25.0.0"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.42.0/llama_cpp_binaries-0.42.0-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/v0.46.0/llama_cpp_binaries-0.46.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and platform_release < "25.0.0"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.46.0/llama_cpp_binaries-0.46.0-py3-none-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"

6
requirements/portable/requirements_apple_silicon.txt
View file

@ -19,6 +19,6 @@ sse-starlette==1.6.5
tiktoken
# Mac wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.42.0/llama_cpp_binaries-0.42.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and platform_release < "25.0.0"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.42.0/llama_cpp_binaries-0.42.0-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/v0.42.0/llama_cpp_binaries-0.42.0-py3-none-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.46.0/llama_cpp_binaries-0.46.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and platform_release < "25.0.0"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.46.0/llama_cpp_binaries-0.46.0-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/v0.46.0/llama_cpp_binaries-0.46.0-py3-none-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0"

4
requirements/portable/requirements_cpu_only.txt
View file

@ -19,5 +19,5 @@ sse-starlette==1.6.5
tiktoken
# llama.cpp (CPU only, AVX2)
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.42.0/llama_cpp_binaries-0.42.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.42.0/llama_cpp_binaries-0.42.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.46.0/llama_cpp_binaries-0.46.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.46.0/llama_cpp_binaries-0.46.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows"

4
requirements/portable/requirements_cpu_only_noavx2.txt
View file

@ -19,5 +19,5 @@ sse-starlette==1.6.5
tiktoken
# llama.cpp (CPU only, no AVX2)
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.42.0/llama_cpp_binaries-0.42.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.42.0/llama_cpp_binaries-0.42.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.46.0/llama_cpp_binaries-0.46.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.46.0/llama_cpp_binaries-0.46.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows"

4
requirements/portable/requirements_noavx2.txt
View file

@ -19,5 +19,5 @@ sse-starlette==1.6.5
tiktoken
# CUDA wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.42.0/llama_cpp_binaries-0.42.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.42.0/llama_cpp_binaries-0.42.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.46.0/llama_cpp_binaries-0.46.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.46.0/llama_cpp_binaries-0.46.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"

4
requirements/portable/requirements_vulkan.txt
View file

@ -19,5 +19,5 @@ sse-starlette==1.6.5
tiktoken
# CUDA wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.42.0/llama_cpp_binaries-0.42.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.42.0/llama_cpp_binaries-0.42.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.46.0/llama_cpp_binaries-0.46.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.46.0/llama_cpp_binaries-0.46.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"

4
requirements/portable/requirements_vulkan_noavx2.txt
View file

@ -19,5 +19,5 @@ sse-starlette==1.6.5
tiktoken
# CUDA wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.42.0/llama_cpp_binaries-0.42.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.42.0/llama_cpp_binaries-0.42.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.46.0/llama_cpp_binaries-0.46.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.46.0/llama_cpp_binaries-0.46.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"