You are a competitive programmer, and you are my teammate. We are on Leetcode contest together, and I want you to solve this question:
{{ Problem Title }}
{{ Description }}
Example 1:
{{ Input, output, and explanation (if any) for example 1 }}
| Model | Context Length | GPU Offload | CPU Thread Pool Size | Evaluation Batch Size | Number of Experts | Number of layers to force the experts to CPU | Temperature | Top K Sampling | Repeat Penalty | Top P Sampling | Min P Sampling | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| allenai/Olmo-3-7B-Think | 7729 | 32 | 8 | 512 | - | - | 0.6 | 40 | 1.1 | 0.95 | 0.05 | |
| lm-provers/QED-Nano | 84878 | 36 | 8 | 784 | - | - | 0.6 | 40 | 1.1 | 0.95 | 0.05 | |
| mradermacher/Nemotron-Cascade-2-30B-A3B-GGUF | 16384 | 52 | 8 | 784 | 8 | 8 | 1 | 40 | 1.1 | 0.95 | 0.05 | |
| microsoft/Phi-4-mini-reasoning | 60319 | 32 | 8 | 784 | - | - | 0.8 | 40 | 1.1 | 0.95 | 0.05 | |
| bartowski/nvidia_OpenMath-Nemotron-14B-GGUF | 25844 | 48 | 8 | 784 | - | - | 0.6 | 40 | 1.1 | 0.95 | 0.05 | |
| inclusionAI/Ring-mini-2.0 | 4096 | 20 | 8 | 784 | 8 | 0 | 0.6 | 40 | 1.1 | 0.95 | 0.05 |
| Problem | Performance Metrics | qwen2.5-1.5b-vibethinker-heretic-uncensored-abliterated | qwen/qwen3-coder-30b | |
|---|---|---|---|---|
| Palindrome Partitioning | Runtime (in ms) | 47 | 44 | |
| Memory (in MB) | 33.3 | 34.2 | ||
| IPO | Runtime (in ms) | 231 | 425 | |
| Memory (in MB) | 47.9 | 45.4 | ||
| Maximum Product Subarray | Runtime (in ms) | 3 | 7 | |
| Memory (in MB) | 19.7 | 19.8 | ||
| Dungeon Game | Runtime (in ms) | 3 | 3 | |
| Memory (in MB) | 20.1 | 20.1 | ||
| House Robber II | Runtime (in ms) | 0 | 0 |
You are a competitive programmer, and you are my teammate. We are on Leetcode contest together, and I want you to solve this question:
{{ Problem Title }}
{{ Description }}
Example 1:
{{ Input, output, and explanation (if any) for example 1 }}
| Model | Context Length | GPU Offload | CPU Thread Pool Size | Evaluation Batch Size | Number of Experts | Number of layers to force the experts to CPU | Temperature | Top K Sampling | Repeat Penalty | Top P Sampling | Min P Sampling | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| qwen2.5-1.5b-vibethinker-heretic-uncensored-abliterated | 131072 | 28 | 8 | 784 | - | - | 0.8 | 40 | 1.1 | 0.95 | 0.05 | |
| qwen/qwen3-coder-30b | 64213 | 48 | 8 | 784 | 8 | 8 | 0.7 | 20 | 1.05 | 0.8 | 0.05 |
| name: Build and Deploy Image | |
| on: | |
| push: | |
| branches: | |
| - "main" | |
| jobs: | |
| Main: | |
| runs-on: ubuntu-20.04 | |
| steps: | |
| - name: Checkout repository code |
| # GKE cluster | |
| resource "google_container_cluster" "primary" { | |
| name = "${var.project_id}-gke" | |
| location = var.region | |
| # We can't create a cluster with no node pool defined, but we want to only use | |
| # separately managed node pools. So we create the smallest possible default | |
| # node pool and immediately delete it. | |
| remove_default_node_pool = true | |
| initial_node_count = 1 |
| # VPC | |
| resource "google_compute_network" "vpc" { | |
| name = "${var.project_id}-vpc" | |
| auto_create_subnetworks = "false" | |
| } | |
| # Subnet | |
| resource "google_compute_subnetwork" "subnet" { | |
| name = "${var.project_id}-subnet" | |
| region = var.region |
| data "google_client_config" "primary" { | |
| depends_on = [google_container_cluster.primary] | |
| } | |
| provider "kubernetes" { | |
| host = "https://${google_container_cluster.primary.endpoint}" | |
| token = data.google_client_config.primary.access_token | |
| client_certificate = google_container_cluster.primary.master_auth.0.client_certificate | |
| client_key = google_container_cluster.primary.master_auth.0.client_key | |
| cluster_ca_certificate = base64decode( |
| FROM python:3.9.10-slim-bullseye | |
| COPY requirements.txt requirements.txt | |
| RUN pip3 install -r requirements.txt | |
| COPY main.py . | |
| EXPOSE 8000 | |
| CMD ["uvicorn", "main:app", "--host", "0.0.0.0"] |