e489ad7a21
- **Add SPDX license headers to python source files**
- **Check for SPDX headers using pre-commit**
commit 9d7ef44c3cfb72ca4c32e1c677d99259d10d4745
Author: Russell Bryant <rbryant@redhat.com>
Date: Fri Jan 31 14:18:24 2025 -0500
Add SPDX license headers to python source files
This commit adds SPDX license headers to python source files as
recommended to
the project by the Linux Foundation. These headers provide a concise way
that is
both human and machine readable for communicating license information
for each
source file. It helps avoid any ambiguity about the license of the code
and can
also be easily used by tools to help manage license compliance.
The Linux Foundation runs license scans against the codebase to help
ensure
we are in compliance with the licenses of the code we use, including
dependencies. Having these headers in place helps that tool do its job.
More information can be found on the SPDX site:
- https://spdx.dev/learn/handling-license-info/
Signed-off-by: Russell Bryant <rbryant@redhat.com>
commit 5a1cf1cb3b80759131c73f6a9dddebccac039dea
Author: Russell Bryant <rbryant@redhat.com>
Date: Fri Jan 31 14:36:32 2025 -0500
Check for SPDX headers using pre-commit
Signed-off-by: Russell Bryant <rbryant@redhat.com>
---------
Signed-off-by: Russell Bryant <rbryant@redhat.com>
184 lines
6.9 KiB
Python
184 lines
6.9 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
"""Tests which cover integration of the speculative decoding framework with
|
|
tensor parallelism.
|
|
"""
|
|
|
|
from typing import Optional
|
|
|
|
import pytest
|
|
import torch
|
|
|
|
from vllm.platforms import current_platform
|
|
|
|
from .conftest import run_equality_correctness_test_tp
|
|
|
|
|
|
@pytest.mark.skipif(torch.cuda.device_count() < 2,
|
|
reason="Need at least 2 GPUs to run the test.")
|
|
@pytest.mark.parametrize(
|
|
"common_llm_kwargs",
|
|
[[
|
|
# Skip cuda graph recording for fast test.
|
|
"--enforce-eager",
|
|
"--tensor-parallel-size",
|
|
"2"
|
|
]])
|
|
@pytest.mark.parametrize("per_test_common_llm_kwargs", [[]])
|
|
@pytest.mark.parametrize("baseline_llm_kwargs", [[]])
|
|
@pytest.mark.parametrize("test_llm_kwargs", [
|
|
[
|
|
"--speculative-model",
|
|
"JackFram/llama-68m",
|
|
"--num-speculative-tokens",
|
|
"3",
|
|
],
|
|
[
|
|
"--speculative-model",
|
|
"[ngram]",
|
|
"--num-speculative-tokens",
|
|
"5",
|
|
"--ngram-prompt-lookup-max",
|
|
"3",
|
|
],
|
|
])
|
|
@pytest.mark.parametrize("batch_size", [2])
|
|
@pytest.mark.parametrize(
|
|
"output_len",
|
|
[
|
|
# Use smaller output len for fast test.
|
|
32,
|
|
])
|
|
@pytest.mark.parametrize("seed", [1])
|
|
def test_target_model_tp_gt_1(common_llm_kwargs, per_test_common_llm_kwargs,
|
|
baseline_llm_kwargs, test_llm_kwargs,
|
|
batch_size: int, output_len: int, seed: int):
|
|
"""Verify greedy equality when tensor parallelism is used.
|
|
"""
|
|
if current_platform.is_rocm():
|
|
pytest.skip("hip is not well-supported yet")
|
|
run_equality_correctness_test_tp("JackFram/llama-68m",
|
|
common_llm_kwargs,
|
|
per_test_common_llm_kwargs,
|
|
baseline_llm_kwargs,
|
|
test_llm_kwargs,
|
|
batch_size,
|
|
output_len,
|
|
seed,
|
|
temperature=0.0)
|
|
|
|
|
|
@pytest.mark.skipif(torch.cuda.device_count() < 2,
|
|
reason="Need at least 2 GPUs to run the test.")
|
|
@pytest.mark.parametrize(
|
|
"common_llm_kwargs",
|
|
[[
|
|
# Skip cuda graph recording for fast test.
|
|
"--enforce-eager",
|
|
"--tensor_parallel_size",
|
|
"2",
|
|
|
|
# precision
|
|
"--dtype",
|
|
"bfloat16",
|
|
]])
|
|
@pytest.mark.parametrize("per_test_common_llm_kwargs", [[]])
|
|
@pytest.mark.parametrize("baseline_llm_kwargs", [[]])
|
|
@pytest.mark.parametrize("model, test_llm_kwargs",
|
|
[("JackFram/llama-68m", [
|
|
"--speculative-model",
|
|
"JackFram/llama-68m",
|
|
"--num_speculative-tokens",
|
|
"5",
|
|
"--speculative-draft-tensor-parallel-size",
|
|
"1",
|
|
]),
|
|
("ibm-granite/granite-3b-code-instruct", [
|
|
"--speculative-model",
|
|
"ibm-granite/granite-3b-code-instruct",
|
|
"--num_speculative-tokens",
|
|
"5",
|
|
"--speculative-draft-tensor-parallel-size",
|
|
"1",
|
|
])])
|
|
@pytest.mark.parametrize("batch_size", [2])
|
|
@pytest.mark.parametrize("seed", [1])
|
|
def test_draft_model_tp_lt_target_model_tp2(model, common_llm_kwargs,
|
|
per_test_common_llm_kwargs,
|
|
baseline_llm_kwargs,
|
|
test_llm_kwargs, batch_size: int,
|
|
seed: int):
|
|
"""Verify spec decode works well with smaller tp for draft models.
|
|
"""
|
|
run_equality_correctness_test_tp(model,
|
|
common_llm_kwargs,
|
|
per_test_common_llm_kwargs,
|
|
baseline_llm_kwargs,
|
|
test_llm_kwargs,
|
|
batch_size,
|
|
max_output_len=32,
|
|
seed=seed,
|
|
temperature=0.0)
|
|
|
|
|
|
@pytest.mark.skipif(torch.cuda.device_count() < 2,
|
|
reason="Need at least 2 GPUs to run the test.")
|
|
@pytest.mark.parametrize(
|
|
"common_llm_kwargs",
|
|
[[
|
|
# Skip cuda graph recording for fast test.
|
|
"--enforce-eager",
|
|
"--tensor_parallel_size",
|
|
"2",
|
|
|
|
# precision
|
|
"--dtype",
|
|
"bfloat16",
|
|
]])
|
|
@pytest.mark.parametrize(
|
|
"per_test_common_llm_kwargs",
|
|
[["--enable-chunked-prefill", "False"],
|
|
[
|
|
"--enable-chunked-prefill", "True", "--max-num-batched-tokens", "4",
|
|
"--max-num-seqs", "4"
|
|
]])
|
|
@pytest.mark.parametrize("baseline_llm_kwargs", [[]])
|
|
@pytest.mark.parametrize("model, test_llm_kwargs",
|
|
[("JackFram/llama-68m", [
|
|
"--speculative-model",
|
|
"JackFram/llama-68m",
|
|
"--num_speculative-tokens",
|
|
"3",
|
|
]),
|
|
("JackFram/llama-68m", [
|
|
"--speculative-model",
|
|
"JackFram/llama-68m",
|
|
"--num_speculative-tokens",
|
|
"3",
|
|
"--speculative-draft-tensor-parallel-size",
|
|
"1",
|
|
])])
|
|
@pytest.mark.parametrize("logprobs", [None, 2])
|
|
@pytest.mark.parametrize("batch_size", [2])
|
|
@pytest.mark.parametrize("seed", [1])
|
|
def test_spec_decode_chunked_prefill_tp2(model, common_llm_kwargs,
|
|
per_test_common_llm_kwargs,
|
|
baseline_llm_kwargs, test_llm_kwargs,
|
|
logprobs: Optional[int],
|
|
batch_size: int, seed: int):
|
|
"""Verify spec decode works well with same and different TP size for
|
|
the draft model with chunked prefill.
|
|
"""
|
|
if logprobs:
|
|
test_llm_kwargs.extend(
|
|
["--disable_logprobs_during_spec_decoding", "False"])
|
|
run_equality_correctness_test_tp(model,
|
|
common_llm_kwargs,
|
|
per_test_common_llm_kwargs,
|
|
baseline_llm_kwargs,
|
|
test_llm_kwargs,
|
|
batch_size,
|
|
max_output_len=32,
|
|
seed=seed,
|
|
temperature=0.0,
|
|
logprobs=logprobs)
|