gortium/infra
1
1
Fork 0
Code Issues 13 Pull Requests 21 Actions Packages Projects 1 Releases Wiki Activity

Consolidate cron job docs into single README.md

Browse Source
This commit is contained in:
Hermes Agent
2026-04-28 17:26:21 +00:00
parent 30f8ca3863
commit 7ce0e46670
2 changed files with 74 additions and 346 deletions
Download Patch File Download Diff File Expand all files Collapse all files

283
assets/ai-optimizer/CRON_JOB_DRAFT.md
View File

@@ -1,283 +0,0 @@
# AI Model Optimization Cron Job
**Goal:** Find optimal configurations for maximum context size with full hardware utilization.
**Hardware:**
- 2× AMD MI50 GPUs (32GB VRAM each, 64GB total)
- 128GB system RAM
- ROCm: HSA_OVERRIDE_GFX_VERSION=9.0.6, HIP_VISIBLE_DEVICES=0,1
---
## Model Queue
### GPU-Optimized (Coding - prioritize speed + context on GPU)
1. `devstral-small-2:24b` - Best coding model
2. `qwen2.5-coder:32b` - Strong coder, fits on GPU+offload
3. `codellama:34b-instruct` - Legacy but solid
### RAM-Optimized (Knowledge - prioritize max context, accept slower)
1. `qwen2.5:72b` - Best knowledge, needs heavy offload
2. `nemotron-3-nano:30b` - Good general knowledge
3. `mixtral:8x7b-instruct` - MoE, efficient for knowledge
---
## Optimization Strategy
**Two separate tracks:**
### Track A: GPU-Focused (Coding)
```
Baseline: num_ctx=32768, num_gpu=99, flash_attn=true
Steps:
1. Increase context: 32k → 65k → 98k → 131k → 163k
2. At each step, verify VRAM usage < 60GB (leave headroom)
3. If OOM: reduce num_gpu until stable, record best
4. Measure tokens/sec - if < 5 tok/s, consider context too high
```
### Track B: RAM-Focused (Knowledge)
```
Baseline: num_ctx=65536, num_gpu=50, flash_attn=true
Steps:
1. Increase context: 65k → 131k → 200k → 262k → 327k
2. Allow heavy RAM offload (system RAM up to 100GB)
3. If OOM: reduce context or num_gpu
4. Speed less critical - focus on max stable context
```
---
## Backend-Specific Configs
### Ollama (Modelfile parameters)
```
PARAMETER num_ctx <value>
PARAMETER num_gpu <layers>
PARAMETER flash_attn true/false
PARAMETER num_predict 4096
PARAMETER num_keep 1024
PARAMETER repeat_penalty 1.1
```
### Llama.cpp (CLI flags)
```
--ctx-size <value>
--n-gpu-layers <layers>
--flash-attn on/off
--n-predict 4096
--batch-size 4096
--ubatch-size 512
--cache-type-k f16
--cache-type-v f16
--split-mode layer
--no-mmap
```
---
## Host Test Instructions
**The cron runs inside the hermes container. Some tests require host access:**
### 1. VRAM Monitoring (HOST)
```bash
# Run on host to check VRAM usage during/after benchmark
sudo rocm-smi --showmeminfo vram
# Or via docker exec if rocm-smi available in container
docker exec --privileged ollama rocm-smi --showmeminfo vram
```
### 2. Running Ollama Benchmarks (CONTAINER)
```bash
# Pull model
docker exec ollama ollama pull <model>
# Create custom modelfile
docker exec ollama bash -c 'cat <<EOF > /root/.ollama/test.modelfile
FROM <model>
PARAMETER num_ctx 65536
PARAMETER num_gpu 99
PARAMETER flash_attn true
EOF'
# Create model from modelfile
docker exec ollama ollama create test-model -f /root/.ollama/test.modelfile
# Run benchmark (warm model first)
docker exec ollama ollama run test-model "Write a Python async context manager with exponential backoff"
# Cleanup
docker exec ollama ollama rm test-model
```
### 3. Running Llama.cpp Benchmarks (CONTAINER - needs llama.cpp container)
```bash
# Uncomment llama_cpp_devstral in compose.yml first
# Then rebuild: sudo nh os switch --flake .#lazyworkhorse
# Test via HTTP API
curl http://localhost:8300/v1/completions \
-H "Content-Type: application/json" \
-d '{
"model": "devstral-2-small-llama_cpp",
"prompt": "Write a Python function",
"max_tokens": 100
}'
```
### 4. Deploying Changes (HOST via ai-worker)
```bash
# After optimization, commit results
cd /home/ai-worker/infra
git add assets/ai-optimizer/
git commit -m "ai-optimizer: new best config for <model>"
git push
# If config changes needed in ollama_init_custom_models.nix:
# 1. Edit the file
# 2. nixpkgs-fmt .
# 3. Show diff to user
# 4. Wait for confirmation
# 5. sudo nh os switch --flake .#lazyworkhorse
```
### 5. Accessing Host from Hermes Container
```bash
# SSH to host as ai-worker (key should be mounted)
ssh -i /path/to/key ai-worker@host.docker.internal
# Or via docker socket if mounted
# (not recommended for security)
```
---
## Benchmark Prompts
### Coding (Track A)
```
"Write a Python async context manager that retries a function with exponential backoff, max 5 retries, and logs each attempt using structlog. Include type hints and error handling."
```
### Knowledge (Track B)
```
"Explain the complete memory hierarchy in modern GPUs, from registers through L1/L2 caches to VRAM, and how data moves between them during matrix multiplication. Include bandwidth considerations for each level."
```
### Measurement
- Tokens per second (generation speed)
- Time to first token (latency)
- VRAM usage (via rocm-smi)
- System RAM usage (via free -h)
- Context success (did it complete without OOM?)
---
## State File Structure
`/opt/data/infra/assets/ai-optimizer/state.json`
```json
{
"track": "gpu",
"current_model": "devstral-small-2:24b",
"model_index": 0,
"phase": "context_scaling",
"backend": "ollama",
"current_config": {
"num_ctx": 65536,
"num_gpu": 99,
"flash_attn": true
},
"best_configs": {
"gpu": {
"devstral-small-2:24b": {
"backend": "ollama",
"num_ctx": 131072,
"num_gpu": 99,
"flash_attn": true,
"tokens_per_sec": 12.5,
"vram_used_gb": 58.2,
"tested_at": "2026-04-28T17:00:00Z"
}
},
"ram": {}
},
"completed_models": [],
"gpu_queue": ["devstral-small-2:24b", "qwen2.5-coder:32b", "codellama:34b-instruct"],
"ram_queue": ["qwen2.5:72b", "nemotron-3-nano:30b", "mixtral:8x7b-instruct"]
}
```
---
## Results CSV
`/opt/data/infra/assets/ai-optimizer/results.csv`
```csv
timestamp,track,model,backend,phase,num_ctx,num_gpu,flash_attn,tokens_per_sec,vram_gb,ram_gb,status,is_best
2026-04-28T17:00:00Z,gpu,devstral-small-2:24b,ollama,context_scaling,65536,99,true,15.2,52.1,18.4,success,false
```
---
## Cron Job Flow
```
1. Read state.json
2. If both queues empty → STOP (all models tested)
3. Select next model from current track queue
4. Pull model if needed (docker exec ollama ollama pull)
5. Create Modelfile / llama.cpp config with current test params
6. Run benchmark (both prompts)
7. Measure: tokens/sec, VRAM (rocm-smi), RAM (free -h)
8. If successful:
- Increase context (next step)
- Update current_config in state
9. If OOM/error:
- Record last good config as best_configs[track][model]
- Move to next model in queue
10. Update state.json
11. Append to results.csv
12. Git commit + push to /opt/data/infra
13. Send Matrix notification if available, else silent
```
---
## Matrix Notification (Optional)
```python
# If matrix credentials available in environment
if os.getenv("MATRIX_HOME_SERVER") and os.getenv("MATRIX_ACCESS_TOKEN"):
# Send completion notification
# Room: !ai-optimizer:lazyworkhorse.net (or similar)
pass
# Else: silent, just commit
```
---
## Files to Create
```
/opt/data/infra/assets/ai-optimizer/
├── state.json # Current progress
├── results.csv # All test results
├── best_configs.json # Final best configs (human-readable)
└── CRON_JOB_DRAFT.md # This file
```
---
## Notes
- **No num_parallel**: Removed to avoid limiting other settings
- **Two tracks**: GPU (coding/speed) vs RAM (knowledge/context)
- **Both backends**: Test ollama first, then llama.cpp if available
- **Host tests**: rocm-smi must run on host or privileged container
- **Deploy**: ai-worker has sudo for nh/nixos-rebuild, must ask user first

135
assets/ai-optimizer/CRON_EXECUTION_PROMPT.md → assets/ai-optimizer/README.md
View File

@@ -1,12 +1,8 @@
# AI Model Optimization Cron Job - EXECUTION PROMPT # AI Model Optimization Cron Job
**When this cron runs, follow these instructions exactly:** **Purpose:** Automatically find optimal ollama/llama.cpp configurations for maximum context size and hardware utilization.
--- **Schedule:** Every hour
## Your Role
You are an AI model optimization agent. Your task is to find the best ollama/llama.cpp configuration for maximum context size and hardware utilization.
**Hardware:** **Hardware:**
- 2× AMD MI50 GPUs (32GB VRAM each, 64GB total) - 2× AMD MI50 GPUs (32GB VRAM each, 64GB total)
@@ -20,7 +16,7 @@ You are an AI model optimization agent. Your task is to find the best ollama/lla
``` ```
STATE: /opt/data/infra/assets/ai-optimizer/state.json STATE: /opt/data/infra/assets/ai-optimizer/state.json
RESULTS: /opt/data/infra/assets/ai-optimizer/results.csv RESULTS: /opt/data/infra/assets/ai-optimizer/results.csv
INFRA_REPO: /opt/data/infra REPO: /opt/data/infra (persistent - do not reclone)
``` ```
--- ---
@@ -46,6 +42,22 @@ INFRA_REPO: /opt/data/infra
--- ---
## Optimization Strategy
### GPU Track (Coding)
- Start: num_ctx=32768, num_gpu=99, flash_attn=true
- Increase context until OOM or tokens/sec < 5
- Record best config before hitting wall
- Target: >10 tokens/sec with max context
### RAM Track (Knowledge)
- Start: num_ctx=65536, num_gpu=50, flash_attn=true
- Allow heavy RAM offload (up to 100GB system RAM)
- Increase context until OOM
- Speed secondary to context size
---
## Each Run - Step by Step ## Each Run - Step by Step
### 1. Read State ### 1. Read State
@@ -56,9 +68,9 @@ cat assets/ai-optimizer/state.json
### 2. Determine Next Test ### 2. Determine Next Test
- Read `track` (gpu or ram) - Read `track` (gpu or ram)
- Read `current_model` from queue at `model_index` - Get `current_model` from queue at `model_index`
- Read `current_config` for parameters to test - Get `current_config` for parameters to test
- Select next context step from `context_steps` based on `phase` - Select next context step from `context_steps`
### 3. Pull Model (if needed) ### 3. Pull Model (if needed)
```bash ```bash
@@ -86,11 +98,10 @@ docker exec ollama ollama create test-model -f /root/.ollama/test_${model}.model
docker exec ollama ollama run test-model "Hello" > /dev/null docker exec ollama ollama run test-model "Hello" > /dev/null
# Coding prompt # Coding prompt
START=$(date +%s%N)
docker exec ollama ollama run test-model "Write a Python async context manager that retries a function with exponential backoff, max 5 retries, and logs each attempt using structlog. Include type hints." docker exec ollama ollama run test-model "Write a Python async context manager that retries a function with exponential backoff, max 5 retries, and logs each attempt using structlog. Include type hints."
END=$(date +%s%N)
# Calculate tokens/sec from output # Knowledge prompt
docker exec ollama ollama run test-model "Explain the complete memory hierarchy in modern GPUs, from registers through L1/L2 caches to VRAM, and how data moves between them during matrix multiplication."
``` ```
### 6. Measure VRAM (if possible) ### 6. Measure VRAM (if possible)
@@ -99,33 +110,25 @@ END=$(date +%s%N)
rocm-smi --showmeminfo vram 2>/dev/null || \ rocm-smi --showmeminfo vram 2>/dev/null || \
# Try via docker # Try via docker
docker exec --privileged ollama rocm-smi --showmeminfo vram 2>/dev/null || \ docker exec --privileged ollama rocm-smi --showmeminfo vram 2>/dev/null || \
# Fallback echo "VRAM unavailable"
echo "VRAM measurement unavailable"
``` ```
### 7. Record Results ### 7. Record Results
- Parse tokens/sec from ollama output - Parse tokens/sec from ollama output
- Record VRAM/RAM usage - Record VRAM/RAM usage
- Determine if this is best config so far for this model - Update `best_configs` if improved
- Update `best_configs` if tokens/sec improved or context increased
### 8. Update State ### 8. Update State
```python ```python
# Logic:
if test_successful: if test_successful:
if context_step < max_reached: if context_step < max_reached:
phase = "context_scaling"
current_config.num_ctx = next_context_step current_config.num_ctx = next_context_step
else: else:
# Move to next model
model_index += 1 model_index += 1
phase = "context_scaling"
current_config.num_ctx = context_steps[0] current_config.num_ctx = context_steps[0]
else: else:
# OOM or error - record last good as best
best_configs[track][current_model] = last_good_config best_configs[track][current_model] = last_good_config
model_index += 1 model_index += 1
phase = "context_scaling"
``` ```
### 9. Commit to Repo ### 9. Commit to Repo
@@ -133,71 +136,79 @@ else:
cd /opt/data/infra cd /opt/data/infra
git add assets/ai-optimizer/ git add assets/ai-optimizer/
git commit -m "ai-optimizer: tested ${model} at ${num_ctx} ctx - ${status}" git commit -m "ai-optimizer: tested ${model} at ${num_ctx} ctx - ${status}"
git push origin master git push
``` ```
### 10. Matrix Notification (if available) ### 10. Matrix Notification (if available)
```python ```python
import os import os
if os.getenv("MATRIX_HOME_SERVER") and os.getenv("MATRIX_ACCESS_TOKEN"): if os.getenv("MATRIX_HOME_SERVER") and os.getenv("MATRIX_ACCESS_TOKEN"):
# Send notification to Matrix room # Send notification
# Room ID from env or config
pass pass
# Else: silent # Else: silent
``` ```
--- ---
## State File Structure
```json
{
"track": "gpu",
"current_model": "devstral-small-2:24b",
"model_index": 0,
"phase": "context_scaling",
"backend": "ollama",
"current_config": {
"num_ctx": 32768,
"num_gpu": 99,
"flash_attn": true
},
"best_configs": {
"gpu": {},
"ram": {}
},
"completed_models": [],
"gpu_queue": ["devstral-small-2:24b", "qwen2.5-coder:32b", "codellama:34b-instruct"],
"ram_queue": ["qwen2.5:72b", "nemotron-3-nano:30b", "mixtral:8x7b-instruct"],
"context_steps": [32768, 65536, 98304, 131072, 163840, 200704, 262144, 327680],
"last_updated": "2026-04-28T17:00:00Z"
}
```
---
## Results CSV Format
```csv
timestamp,track,model,backend,phase,num_ctx,num_gpu,flash_attn,tokens_per_sec,vram_gb,ram_gb,status,is_best
2026-04-28T17:00:00Z,gpu,devstral-small-2:24b,ollama,context_scaling,65536,99,true,15.2,52.1,18.4,success,false
```
---
## Stop Conditions ## Stop Conditions
1. All models in both queues have `best_configs` recorded 1. All models in both queues have `best_configs` recorded
2. Manual intervention needed (error in state.json `error` field) 2. Manual intervention needed (error in state.json `error` field)
3. No progress for 3 consecutive runs (stuck) 3. No progress for 3 consecutive runs
--- ---
## Error Handling ## Error Handling
If any step fails: If any step fails:
1. Log error to state.json: `"error": {"message": "...", "timestamp": "..."}` 1. Log error: `"error": {"message": "...", "timestamp": "..."}`
2. Do NOT increment model_index (retry next run) 2. Do NOT increment model_index (retry next run)
3. Commit state with error field 3. Commit state with error field
4. Exit gracefully 4. Exit gracefully
--- ---
## Important Notes ## Notes
- **No num_parallel**: Do not use this parameter - **No num_parallel**: Removed to avoid limiting other settings
- **Two tracks**: Complete GPU track first, then RAM track - **Two tracks**: Complete GPU track first, then RAM track
- **Backend**: Start with ollama, llama.cpp testing is optional (requires uncommenting in compose.yml) - **Backend**: Start with ollama, llama.cpp optional
- **Host access**: Some commands need host - use docker exec or SSH if available - **Host access**: Use docker exec or SSH for rocm-smi
- **Ask before deploy**: If config changes needed in NixOS modules, show diff and wait for user confirmation before `nh os switch` - **Ask before deploy**: Show diff before `nh os switch`
---
## Example State Transitions
**Start:**
```json
{"track": "gpu", "model_index": 0, "current_model": "devstral-small-2:24b", "current_config": {"num_ctx": 32768, ...}}
```
**After successful test at 32k:**
```json
{"track": "gpu", "model_index": 0, "current_model": "devstral-small-2:24b", "current_config": {"num_ctx": 65536, ...}}
```
**After OOM at 131k:**
```json
{
"track": "gpu",
"model_index": 1,
"current_model": "qwen2.5-coder:32b",
"best_configs": {
"gpu": {
"devstral-small-2:24b": {"num_ctx": 98304, "num_gpu": 99, "tokens_per_sec": 11.2}
}
}
}
```