File size: 13,204 Bytes
c92e699 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 | # SPDX-FileCopyrightText: © 2024 Tenstorrent USA, Inc.
# SPDX-License-Identifier: Apache-2.0
import bz2
import os
import pytest
import torch
from loguru import logger
import ttnn
from models.common.utility_functions import comp_pcc
from models.tt_transformers.tt.common import PagedAttentionConfig, create_tt_model
from models.tt_transformers.tt.generator import Generator
from models.tt_transformers.tt.model_config import DecodersPrecision
@torch.no_grad()
@pytest.mark.timeout(900)
@pytest.mark.models_performance_bare_metal
@pytest.mark.parametrize("use_prefetcher", ([False]))
@pytest.mark.parametrize(
"mesh_device",
[
{"N150": (1, 1), "N300": (1, 2), "T3K": (1, 8), "TG": (8, 4)}.get(
os.environ.get("MESH_DEVICE"), len(ttnn.get_device_ids())
)
],
indirect=True,
)
# Model and attention prefill tests should run both with and without paged attention to debug any issues that may occur with default attention
@pytest.mark.parametrize(
"paged_attention",
(
True,
# False,
),
ids=(
"paged_attention",
# "default_attention",
),
)
@pytest.mark.parametrize(
"page_params",
[{"page_block_size": 32, "page_max_num_blocks": 1024}],
)
@pytest.mark.parametrize(
"seq_len",
(128, 256, 3072, 4096, 8192, 16384, 32768),
ids=["128", "256", "3k", "4k", "8k", "16k", "32k"],
)
@pytest.mark.parametrize(
"max_seq_len",
(128 * 1024,),
ids=[
"max128k",
],
)
@pytest.mark.parametrize(
"optimizations",
[
lambda model_args: DecodersPrecision.performance(model_args.n_layers, model_args.model_name),
lambda model_args: DecodersPrecision.accuracy(model_args.n_layers, model_args.model_name),
],
ids=["performance", "accuracy"],
)
@pytest.mark.parametrize(
"num_layers",
(1, None),
ids=["1layer", "all_layers"],
)
@pytest.mark.parametrize("device_params", [{"fabric_config": True}], indirect=True)
def test_model_inference(
paged_attention,
page_params,
optimizations,
seq_len,
max_seq_len,
num_layers,
mesh_device,
reset_seeds,
ensure_gc,
is_ci_env,
request,
use_prefetcher,
):
test_id = request.node.callspec.id
use_hf_rope = request.config.getoption("--use_hf_rope")
if is_ci_env:
if "accuracy" in test_id:
pytest.skip("CI test only runs performance mode to reduce CI pipeline load")
# TODO: Save ref outputs to avoid running reference model for large seq_len
if seq_len > 8192:
pytest.skip("CI test only runs up to 8192 seq_len to avoid out of ram issues for ref model")
if use_hf_rope:
if num_layers != 1 and seq_len != 256:
pytest.skip("When HF rope is used CI only runs full model for 256 seq len to reduce CI pipeline load")
elif num_layers != 1 and seq_len != 4096:
pytest.skip("CI only runs full model for 4k seq len to reduce CI pipeline load")
hf_model_env = os.getenv("HF_MODEL", "")
if ("Llama" in hf_model_env) and ("Vision" in hf_model_env) and (num_layers is None):
pytest.skip("Skipping Llama Vision full model test: no CrossAttention functionality in this test.")
run_ref_pt = True # Flag to run reference PyTorch model and compare PCC
dtype = ttnn.bfloat8_b
batch_size = 1 # For prefill we only support batch_size = 1
# Use instruct weights instead of general weights
instruct = True
paged_attention_config = (
PagedAttentionConfig(
block_size=page_params["page_block_size"],
max_num_blocks=page_params["page_max_num_blocks"],
)
if paged_attention
else None
)
# Load TTNN model
logger.info(f"Loading TT model...")
model_args, tt_model, tt_kv_cache, state_dict = create_tt_model(
mesh_device,
instruct=instruct,
max_batch_size=batch_size,
optimizations=optimizations,
max_seq_len=max_seq_len,
paged_attention_config=paged_attention_config,
dtype=dtype,
num_layers=num_layers,
use_prefetcher=use_prefetcher,
use_hf_rope=use_hf_rope,
)
if (
model_args.base_model_name.startswith("Mistral-")
or model_args.base_model_name.startswith("Qwen3-")
or model_args.base_model_name.startswith("Phi-3-mini-")
or model_args.base_model_name.startswith("phi-4")
):
# TODO: Per layer KV cache fetching is not implemented for all models
# See issue https://github.com/tenstorrent/tt-metal/issues/19806"
cache_pcc = False
else:
cache_pcc = True
# This sets the minimum PCC for each iteration based on optimization mode
# TODO: See issue https://github.com/tenstorrent/tt-metal/issues/19806
perf_out_pcc_map = {"Mistral-7B-Instruct-v0.3": 0.73}
acc_out_pcc_map = {
"Mistral-7B-Instruct-v0.3": 0.75,
"Phi-3-mini-128k-instruct": 0.89,
}
kv_cache_pcc_map = {"Mistral-7B-Instruct-v0.3": 0.75}
if num_layers == 1:
expec_out_pcc = 0.97
expec_kv_cache_pcc = 0.99
else:
if "accuracy" in test_id:
default_expec_out_pcc = 0.91 # TODO Look on improving PCC
expec_out_pcc = acc_out_pcc_map.get(model_args.model_name, default_expec_out_pcc)
else: # performance mode
assert "performance" in test_id
default_expec_out_pcc = 0.869 # TODO Look on improving PCC
expec_out_pcc = perf_out_pcc_map.get(model_args.model_name, default_expec_out_pcc)
default_expec_kv_cache_pcc = 0.88
expec_kv_cache_pcc = kv_cache_pcc_map.get(model_args.model_name, default_expec_kv_cache_pcc)
processor = model_args.processor
tokenizer = model_args.tokenizer
generator = Generator([tt_model], [model_args], mesh_device, processor=processor, tokenizer=tokenizer)
logger.info("Finished loading TT model.")
# Create page table if paged attention is enabled
if paged_attention:
# Implied shuffling of blocks
permutation = torch.randperm(paged_attention_config.max_num_blocks)
# Page table which maps virtual blocks to physical
reverse_permutation = torch.argsort(permutation)
page_table = reverse_permutation.reshape(
model_args.max_batch_size, paged_attention_config.max_num_blocks // model_args.max_batch_size
)
else:
page_table = None
# Load prompt
current_file_path = os.path.abspath(__file__)
current_file_dir = os.path.dirname(current_file_path)
prompt_file = os.path.join(current_file_dir, "tale-of-two-cities.txt.bz2")
with bz2.open(prompt_file, "rt", encoding="utf-8") as f:
prompt = f.read()
encoded_prompt = model_args.encode_prompt(prompt, instruct=instruct)[:seq_len]
logger.info(f"Prompt length: {len(encoded_prompt)} tokens")
# Load reference model
if run_ref_pt:
logger.info("Loading reference model...")
# On a warm ttnn cache, create_tt_model defers the HF load and returns a dataless
# placeholder state_dict. The host reference embedding below still needs the REAL weights,
# so reload them here when the state_dict is a warm-cache placeholder (either flavor) or
# genuinely empty. Branch on is_placeholder, NOT truthiness: tt_transformers'
# _PlaceholderStateDict is falsy but the shared CachedStateDict is truthy, so `if not
# state_dict` alone would silently stop reloading -- and build this torch reference from
# torch.empty garbage -- if the loaders are ever collapsed onto the shared class. (#45400)
if getattr(state_dict, "is_placeholder", False) or not state_dict:
state_dict = model_args.load_state_dict()
state_dict_prefix = model_args.get_state_dict_prefix("", None)
reference_model = model_args.reference_transformer(load_checkpoint=True)
# Embedding on host
embd = model_args.reference_embedding()
if model_args.is_llama_vision():
weight = torch.cat(
[
state_dict[f"{state_dict_prefix}tok_embeddings.weight"],
state_dict[f"{state_dict_prefix}learnable_embedding.weight"],
],
dim=0,
)
else:
weight = state_dict[f"{state_dict_prefix}tok_embeddings.weight"]
embd.load_state_dict({"emb.weight": weight})
logger.info("Finished loading reference model.")
# Select the first token from the prompt for initial decoding
encoded_prompt_tensor = torch.tensor(encoded_prompt) # [:,0]
tt_prefill_input = encoded_prompt_tensor.unsqueeze(0)
prompt_lens = [seq_len]
start_pos = 0
# Run TT model
logger.info(f"Running TT model...")
tt_output_torch = generator.prefill_forward_text(
tt_prefill_input,
page_table=page_table,
kv_cache=[tt_kv_cache],
prompt_lens=prompt_lens,
)
logger.info(f"Finished running TT model.")
if run_ref_pt:
# Run reference model
logger.info(f"Running reference model...")
pt_prefill_input = embd(encoded_prompt_tensor).view(batch_size, seq_len, -1)
ref_output = reference_model(pt_prefill_input, start_pos)
ref_output = ref_output[:, -1:, :] # Get last token since TT model only returns the last token
logger.info(f"Finished running reference model.")
# Measure PCC if also running reference model
all_tests_pass = True
# Check output pcc
passing, pcc_message = comp_pcc(ref_output, tt_output_torch, expec_out_pcc)
logger.info(f"Output PCC: {pcc_message}")
if not passing:
all_tests_pass = False
logger.warning(f"Output PCC {pcc_message} is lower than {expec_out_pcc}")
# Compare KV caches
if cache_pcc:
for i in range(model_args.n_layers):
pytorch_layer_present = [
reference_model.cache_k[i].clone().permute(0, 2, 1, 3), # [batch_size, n_kv_heads, seq, head_dim]
reference_model.cache_v[i].clone().permute(0, 2, 1, 3), # [batch_size, n_kv_heads, seq, head_dim]
]
tt_layer_present = []
if paged_attention:
for layer_past in tt_model.layers[i].attention.layer_past:
tt_layer_present.append(
ttnn.to_torch(
layer_past,
mesh_composer=ttnn.ConcatMesh2dToTensor(
mesh_device,
dims=(1, 3) if model_args.is_galaxy else (0, 1),
mesh_shape=model_args.cluster_shape,
),
)[reverse_permutation][:, : model_args.n_kv_heads, :, : model_args.head_dim]
.reshape(
model_args.max_batch_size,
paged_attention_config.max_num_blocks // model_args.max_batch_size,
model_args.n_kv_heads,
paged_attention_config.block_size,
model_args.head_dim,
)
.transpose(1, 2)
.reshape(model_args.max_batch_size, model_args.n_kv_heads, -1, model_args.head_dim)[
:batch_size, ...
]
)
else:
for layer_past in tt_model.layers[i].attention.layer_past_list[0]:
tt_layer_present.append(
ttnn.to_torch(
layer_past,
mesh_composer=ttnn.ConcatMesh2dToTensor(
mesh_device,
dims=(1, 0) if model_args.is_galaxy else (0, 1),
mesh_shape=model_args.cluster_shape,
),
)
)
for j, (cache_pt, cache_tt) in enumerate(zip(pytorch_layer_present, tt_layer_present)):
cache_length_to_check = seq_len
cache_pt = cache_pt[:, :, 0:cache_length_to_check, :]
cache_tt = cache_tt[:, :, 0:cache_length_to_check, :]
pcc_passed, output_pcc = comp_pcc(cache_pt, cache_tt, expec_kv_cache_pcc)
kv_str = "K" if j == 0 else "V"
logger.info(f"[layer={i+1}] {kv_str} cache PCC: {output_pcc}")
if not pcc_passed:
all_tests_pass = False
logger.warning(f"[layer={i+1}] {kv_str} PCC {output_pcc} is lower than {expec_kv_cache_pcc}")
if all_tests_pass:
logger.info("All PCC checks passed!")
else:
assert all_tests_pass, f"PCC is lower than expected for some of the outputs. Check warnings!"
|