Instructions to use EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int8 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int8", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int8", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int8

SGLang

How to use EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int8 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int8" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int8" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int8 with Docker Model Runner:
```
docker model run hf.co/EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int8
```

Laguna-XS.2 → Dense (K=8) · CUDA-SFT · torchao Int8 weight-only

Quantized variant of EvanOLeary/laguna-xs2-dense-k8-cuda-sft. Pure-PyTorch int8 weight-only quantization via torchao. Bf16 activations / compute, int8 storage. Quantization is lossless on greedy decode for the ReLU smoke prompt (byte-identical to bf16).

Size & quality

	bf16 (base)	torchao Int8 weight-only
Weight file	5.99 GB	3.21 GB (54% of bf16)
VRAM (loaded)	6.00 GB	3.22 GB
Bits/param (effective)	16	~8.6 (incl. scale/zero overhead)

ReLU CUDA kernel smoke test (greedy decode, 400 max_new_tokens)

Quantization is functionally lossless on this prompt — int8 output is byte-identical to bf16 (1046 chars, 303 tokens, both greedy).

Prompt: "Write a CUDA kernel that computes ReLU (max(x, 0)) on a float array in-place. Include the kernel and a host-side launcher."

The model produced a complete torch::extension-style CUDA kernel with templated relu_kernel, AT_DISPATCH_FLOATING_TYPES dispatch, a relu_forward host launcher, and a PYBIND11_MODULE entrypoint suitable for torch.utils.cpp_extension.load_inline.

How to load

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

repo = "EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int8"
tok = AutoTokenizer.from_pretrained(repo, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(repo, trust_remote_code=True,
    dtype=torch.bfloat16, device_map="cuda")
# torchao quant is baked into the saved weights — no further setup needed.

msgs = [{"role":"user","content":"Write a CUDA kernel for elementwise sigmoid on a float array."}]
text = tok.apply_chat_template(msgs, add_generation_prompt=True, tokenize=False)
ids = tok(text, return_tensors="pt", add_special_tokens=False).input_ids.to(model.device)
out = model.generate(ids, max_new_tokens=400, do_sample=False, pad_token_id=tok.pad_token_id)
print(tok.decode(out[0][ids.shape[-1]:], skip_special_tokens=True))

Provenance & roadmap

Stage	Repo
Teacher MoE	poolside/Laguna-XS.2
Dense recon (V1)	EvanOLeary/laguna-xs2-dense-k8-recon
CUDA-SFT (bf16 base for this quant)	EvanOLeary/laguna-xs2-dense-k8-cuda-sft
This: torchao Int8 weight-only	EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int8

Quantization details

Library: torchao 0.17.0 Int8WeightOnlyConfig
Scheme: symmetric per-channel int8 weight quantization, bf16 activations & computation
Calibration: none (PTQ on weights only)
Quantize time: 0.4 s after model load
Verification: bf16 vs int8 produce byte-identical 1046-char output on the ReLU prompt (greedy decode)
Inference cost: dequantize-on-the-fly to bf16 per matmul → ~1.34× slower wall-clock than bf16 on A100 (14.8 → 9.8 tok/s). torch.compile should close this gap.

Downloads last month: 21

Model tree for EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int8

Base model

poolside/Laguna-XS.2

Finetuned

EvanOLeary/laguna-xs2-dense-k8-cuda-sft

Finetuned

(3)

this model