Q-TensorFormer / tests /test_systems_and_serving.py
Premchandyadav369
feat(systems): add NVIDIA TRT-LLM plugin, vLLM continuous batching adapter, multi-architecture roofline model, test suite, updated academic papers, and systems research dossier
383a1cd
Raw History Blame Contribute Delete
7.97 kB
"""
tests/test_systems_and_serving.py
Comprehensive test suite verifying Enterprise Systems & Serving Modules:
1. vLLM Continuous Batching and PagedAttention Adapter (src/vllm_adapter.py)
2. NVIDIA TensorRT-LLM Custom Plugin (src/trt_llm_plugin.py)
3. Multi-Architecture Hardware Roofline Analyzer (src/roofline_analyzer.py)
"""
import sys
from pathlib import Path
# Ensure repo root is on sys.path
REPO_ROOT = Path(__file__).resolve().parent.parent
if str(REPO_ROOT) not in sys.path:
sys.path.insert(0, str(REPO_ROOT))
import pytest
import torch
import torch.nn as nn
from src.config import ModelConfig
from src.models import QTensorFormer
from src.vllm_adapter import VLLMContinuousBatchingAdapter, QTensorFormerPagedAttentionMetadata
from src.trt_llm_plugin import QTensorFormerTRTPlugin
from src.roofline_analyzer import EnterpriseRooflineAnalyzer, DecodingRooflineProfile, HardwareRooflineSpec
@pytest.fixture
def tiny_qtf_model():
cfg = ModelConfig(
d_model=64,
n_heads=2,
n_layers=2,
ff_multiplier=2,
max_seq_len=64,
vocab_size=256,
tt_rank=4,
tt_min_rank=1,
use_quantum=False,
)
model = QTensorFormer(cfg)
model.eval()
return model
# =========================================================================
# 1. vLLM Continuous Batching & PagedAttention Tests
# =========================================================================
def test_vllm_paged_attention_metadata_creation():
"""Validates creation and tensor properties of PagedAttention metadata."""
metadata = QTensorFormerPagedAttentionMetadata.create_dummy_metadata(
batch_size=4,
max_seq_len=32,
block_size=16,
device="cpu",
)
assert metadata.block_tables.shape == (4, 2)
assert metadata.slot_mapping.shape == (4 * 32,)
assert metadata.context_lens.shape == (4,)
assert metadata.active_ranks.shape == (4,)
assert metadata.max_context_len == 32
def test_vllm_rank_scheduling_thermal_and_entropy(tiny_qtf_model):
"""Verifies dynamic rank scheduling across varied token entropies and thermal states."""
adapter = VLLMContinuousBatchingAdapter(tiny_qtf_model)
# High, medium, low entropy tokens
entropies = torch.tensor([3.2, 1.8, 0.4])
# Case 1: Normal thermal headroom (> 5.0 C margin)
ranks_normal = adapter.schedule_batch_ranks(
seq_entropies=entropies,
hardware_thermal_margin_c=12.5,
target_latency_budget_ms=25.0,
)
assert ranks_normal == [16, 8, 4]
# Case 2: Severe thermal throttling (< 5.0 C margin)
ranks_throttled = adapter.schedule_batch_ranks(
seq_entropies=entropies,
hardware_thermal_margin_c=3.2,
target_latency_budget_ms=25.0,
)
assert ranks_throttled == [2, 2, 2]
def test_vllm_paged_forward_execution(tiny_qtf_model):
"""Verifies that execute_paged_forward produces correct logits shapes without regression."""
adapter = VLLMContinuousBatchingAdapter(tiny_qtf_model)
metadata = QTensorFormerPagedAttentionMetadata.create_dummy_metadata(
batch_size=2,
max_seq_len=16,
block_size=8,
)
input_ids = torch.randint(0, 256, (2, 16))
positions = torch.arange(16).unsqueeze(0).expand(2, -1)
logits = adapter.execute_paged_forward(
input_ids=input_ids,
positions=positions,
metadata=metadata,
selected_ranks=[4, 8],
)
assert logits.shape == (2, 16, 256)
assert not torch.isnan(logits).any()
# =========================================================================
# 2. NVIDIA TensorRT-LLM Custom Plugin Tests
# =========================================================================
def test_trt_llm_plugin_initialization_and_metadata():
"""Validates IPluginV2DynamicExt contracts and static characteristics."""
plugin = QTensorFormerTRTPlugin(
in_features=64,
out_features=64,
max_tt_rank=8,
in_modes=[4, 4, 4],
out_modes=[4, 4, 4],
dtype=torch.float32,
)
assert plugin.get_plugin_type() == "QTensorFormerPlugin_TRT"
assert plugin.get_plugin_version() == "2.1.0"
# Zero-scratchpad in SMEM contract
assert plugin.get_workspace_size(max_batch_size=8, max_seq_len=128) == 0
def test_trt_llm_plugin_smem_sizing():
"""Verifies that SMEM allocation stays well below the 228 KB Hopper limit."""
plugin = QTensorFormerTRTPlugin(
in_features=64,
out_features=64,
max_tt_rank=8,
in_modes=[4, 4, 4],
out_modes=[4, 4, 4],
)
smem_r1 = plugin.compute_smem_requirement_bytes(active_rank=1)
smem_r8 = plugin.compute_smem_requirement_bytes(active_rank=8)
assert smem_r1 > 0
assert smem_r8 >= smem_r1
assert smem_r8 <= 65536 # Within hardware SM limits
def test_trt_llm_plugin_dynamic_slicing_and_forward():
"""Verifies that forward pass runs correctly across active rank configurations."""
plugin = QTensorFormerTRTPlugin(
in_features=64,
out_features=64,
max_tt_rank=8,
in_modes=[4, 4, 4],
out_modes=[4, 4, 4],
dtype=torch.float32,
)
x = torch.randn(2, 10, 64)
# Test full rank
out_full = plugin(x, active_rank=8)
assert out_full.shape == (2, 10, 64)
assert not torch.isnan(out_full).any()
# Test sliced sub-rank
out_sliced = plugin(x, active_rank=2)
assert out_sliced.shape == (2, 10, 64)
assert not torch.isnan(out_sliced).any()
# Core slicing checks
c1, c2, c3 = plugin.slice_cores(active_rank=2)
assert c1.shape == (1, 4, 4, 2)
assert c2.shape == (2, 4, 4, 2)
assert c3.shape == (2, 4, 4, 1)
# =========================================================================
# 3. Enterprise Roofline Analyzer Tests
# =========================================================================
def test_roofline_analyzer_initialization_all_targets():
"""Verifies hardware specs for Hopper, Blackwell, Thor, Orin, and Raspberry Pi 5."""
targets = [
"blackwell_b200",
"hopper_h100",
"ampere_a100",
"jetson_thor",
"jetson_orin_nano",
"raspberry_pi_5",
]
for key in targets:
analyzer = EnterpriseRooflineAnalyzer(key)
assert analyzer.spec.peak_bandwidth_gb_s > 0
assert analyzer.spec.peak_tensor_tflops > 0
assert analyzer.spec.ridge_point > 0
def test_roofline_analyzer_invalid_key():
"""Ensures unrecognized target raises KeyError with informative message."""
with pytest.raises(KeyError):
EnterpriseRooflineAnalyzer("unknown_supercomputer")
def test_roofline_token_decoding_simulation():
"""Validates operational intensity and speedup calculations."""
analyzer = EnterpriseRooflineAnalyzer("hopper_h100")
profile = analyzer.analyze_token_decoding(
batch_size=1,
seq_len=512,
active_rank=4,
d_model=512,
n_layers=8,
)
assert profile.hardware_name == "NVIDIA Hopper H100 (SXM5)"
assert profile.speedup_ratio >= 1.0
assert profile.dram_traffic_reduction_pct > 80.0
assert profile.qtf_latency_ms_per_token > 0.0
assert profile.dense_latency_ms_per_token > profile.qtf_latency_ms_per_token
assert "DRAM Bandwidth Limited" in profile.dense_regime
def test_roofline_compare_all_and_markdown_table():
"""Validates comparison across all targets and confirms zero em dashes in output."""
comparison = EnterpriseRooflineAnalyzer.compare_all_hardware(batch_size=1, seq_len=512, active_rank=4)
assert len(comparison) == 6
for key, p in comparison.items():
assert p.speedup_ratio > 1.0
table_md = EnterpriseRooflineAnalyzer.generate_roofline_summary_table()
assert "| NVIDIA Hopper H100" in table_md
assert "| NVIDIA Blackwell B200" in table_md
assert "—" not in table_md, "Found forbidden em dash in roofline summary table"