Optimize shape-aware LLM inference batches
Pack every request from two buckets into static-shape batches that obey alignment and shape limits while meeting cost, padding, latency, and time thresholds.
llm-inference-batching-scheduler
Normalized profile
What this task asks for
Pack every request from two buckets into static-shape batches that obey alignment and shape limits while meeting cost, padding, latency, and time thresholds. Include every request exactly once. Use seq_align multiples of 64 with heads_align 32 and hidden_align 4096. Use no more than eight unique shapes across both buckets. Keep shapes identical within a batch. Meet every published per-bucket performance threshold.
Intent
- performance optimization
- configuration tuning
- data transformation
Work surfaces
- batch scheduler
- tensor shapes
Technology
- LLM inference
- static graphs
- JSON Lines
Expected artifacts
- /app/task_file/output_data/plan_b1.jsonl
- /app/task_file/output_data/plan_b2.jsonl
What makes it difficult
- reverse engineering from incomplete or indirect evidence
- strict behavioral compatibility or exact-output validation
- quantitative performance, accuracy, or resource constraints
- cross-language or cross-format integration
Published evidence
Model × harness outcomes
Counts are tied to these exact configurations. Harnesses are not treated as equivalent across benchmarks.
- Models
- 13
- Configurations
- 20
- Trials
- 100
Showing 20 of 20 configurations
| Model | Harness | Effort | Result | Passes |
|---|---|---|---|---|
| claude-fable-5anthropic · 2026-06-07 | claude-code2.1.167 | xhigh | All passed | 5/5 |
| claude-fable-5anthropic · 2026-06-05 | terminus-22.0.0 | high | All passed | 5/5 |
| claude-opus-4-7anthropic · 2026-05-01 | claude-code2.1.123 | max | All passed | 5/5 |
| claude-opus-4-7anthropic · 2026-05-01 | terminus-22.0.0 | max | No passes5 errors | 0/5 |
| claude-opus-4-8anthropic · 2026-07-09 | claude-code2.1.205 | high | Mixed | 4/5 |
| claude-sonnet-5anthropic · 2026-07-09 | claude-code2.1.205 | high | Mixed1 errors | 3/5 |
| gemini-3-pro-previewgemini · 2026-05-01 | gemini-cli0.40.0 | high | All passed | 5/5 |
| gemini-3-pro-previewgemini · 2026-05-01 | terminus-22.0.0 | high | All passed | 5/5 |
| gemini-3.1-pro-previewgemini · 2026-05-05 | gemini-cli0.40.0 | high | Mixed1 errors | 4/5 |
| gemini-3.1-pro-previewgemini · 2026-05-05 | terminus-22.0.0 | high | All passed | 5/5 |
| glm-5.1zai · 2026-05-01 | claude-code2.1.123 | max | Mixed4 errors | 1/5 |
| gpt-5.5openai · 2026-05-01 | codex0.125.0 | xhigh | All passed | 5/5 |
| gpt-5.5openai · 2026-05-01 | terminus-22.0.0 | xhigh | All passed | 5/5 |
| gpt-5.6-lunaopenai · 2026-07-10 | codex0.144.0 | max | All passed | 5/5 |
| gpt-5.6-lunaopenai · 2026-07-11 | codex0.144.1 | max | All passed | 5/5 |
| gpt-5.6-solopenai · 2026-07-10 | codex0.144.0 | max | All passed | 5/5 |
| gpt-5.6-terraopenai · 2026-07-10 | codex0.144.0 | max | All passed | 5/5 |
| gpt-5.6-terraopenai · 2026-07-11 | codex0.144.1 | max | All passed | 5/5 |
| grok-4.5cursor · 2026-07-09 | cursor-cli2026.07.08-0c04a8a | default | All passed | 5/5 |
| muse-spark-1.1openai · 2026-07-09 | mini-swe-agent2.4.5 | xhigh | All passed | 5/5 |