research/optimization-catalog.md

# Optimization Catalog — Detailed Research

*Chef et Dev | Gemma Speed Challenge*

---

## 1. FP8 Quantization (Priority: HIGH)

### Why FP8?
- A10G has native FP8 tensor cores (compute capability 8.9)
- Expected 2x throughput vs BF16 for matmul operations
- Minimal PPL impact if calibration is correct

### Implementation
```bash
# vLLM command line:
--quantization fp8
--load-format fp8
--dtype bfloat16  # compute dtype stays BF16 for stability
```

### Calibration Strategy
1. Use auto-calibration (vLLM handles this)
2. Validate PPL on ground_truth_tokens after each change
3. If PPL > 2.42, switch to fp8_e4m3fnz (more conservative)

### Expected Gains
- Throughput: +15-25%
- PPL impact: minimal if calibrated
- Risk: medium (must validate carefully)

---

## 2. AWQ Int4 Quantization (Priority: HIGH)

### Why AWQ?
- Pre-computed AWQ weights available for Gemma-4
- Better PPL stability than GGUF
- Proven technique for 8B models

### Implementation
```bash
# Requires AWQ weight files:
--model /path/to/gemma-4-E4B-it-awq
--quantization awq
--load-format awq
--dtype float16
```

### Expected Gains
- Throughput: +20-30% (int4 matmul on A10G)
- PPL impact: moderate (usually stays under 2.42)
- Risk: low-medium (well-studied technique)

---

## 3. FlashInfer Attention Backend (Priority: MEDIUM)

### Why FlashInfer?
- Faster than default Triton for gemm-based attention
- Better memory bandwidth utilization
- Already bundled with vLLM 0.22.0

### Implementation
```bash
# Should be automatic with vLLM 0.22.0
# Explicitly set if needed:
--attention-backend flashinfer
```

### Expected Gains
- Throughput: +5-10%
- PPL impact: negligible
- Risk: low

---

## 4. KV Cache Quantization (Priority: MEDIUM)

### Why KV Cache Quantization?
- KV cache dominates VRAM for long contexts
- Quantizing KV cache frees memory for larger batch sizes
- Can be combined with other optimizations

### Implementation
```bash
--quantization fp8  # includes KV cache quantization
# Or explicit KV cache quantization:
--kv-cache-dtype fp8
```

### Expected Gains
- Throughput: +10-15% (indirect, via memory savings)
- PPL impact: small
- Risk: medium

---

## 5. CUDA Graph Optimization (Priority: MEDIUM)

### Why CUDA Graphs?
- Eliminates Python/CUDA overhead per call
- Critical for single-stream benchmark
- vLLM handles this automatically, but needs warmup

### Implementation
```python
# Warmup calls before benchmark:
for i in range(20):
    await client.completions.create(
        model="gemma-4-e4b-it",
        prompt=[...],  # representative prompt
        max_tokens=64,
        temperature=0.0
    )
```

### Expected Gains
- Latency reduction: 5-15ms per request
- Throughput: +5-10% (indirect)
- Risk: low

---

## 6. Scheduler Parameter Tuning (Priority: LOW)

### Key Parameters
- `--max-num-batched-tokens 512` — already set
- `--max-num-seqs 64` — increase for more parallelism
- `--scheduler-delay-factor 0.05` — dynamic scheduling
- `--num-scheduler-steps 10` — batching frequency

### Expected Gains
- Throughput: +2-5%
- PPL impact: negligible
- Risk: low

---

## 7. Layer Removal (Priority: LOW)

### Why Layer Removal?
- Fewer layers = less computation
- Can be effective if PPL allows

### Implementation
- Modify model config to skip top N layers
- Must validate PPL after each removal

### Expected Gains
- Throughput: +10-20% (proportional to layers removed)
- PPL impact: HIGH (often exceeds cap)
- Risk: HIGH

---

## Optimization Strategy

### Recommended Order:
1. **Baseline** (BF16) → establish reference
2. **FlashInfer** → quick win, low risk
3. **FP8 quantization** → high gain, validate PPL
4. **CUDA graph warmup** → optimize timing
5. **AWQ int4** → if FP8 doesn't meet target
6. **KV cache quantization** → combined with FP8
7. **Scheduler tuning** → fine-tuning phase

### Key Constraint: PPL < 2.42
- Every optimization MUST be validated against PPL
- Reference PPL: ~2.30
- 5% margin: 2.30 * 1.05 = 2.415

---

*Last updated: 2026-06-11 by chef-et-dev*