biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Revert "[Redo] #26368 (#28771)" (#29121)

Browse Source 
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
This commit is contained in:
Jialin Ouyang
2025-11-20 21:27:45 -08:00
committed by GitHub
parent 11857a00b0
commit 30b9c67743
16 changed files with 99 additions and 127 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
tests/v1/spec_decode/test_eagle.py
View File

@@ -3,7 +3,6 @@
from unittest import mock
import numpy as np
import pytest
import torch
@@ -113,9 +112,7 @@ def test_prepare_next_token_ids():
sampled_token_ids_tensor = torch.tensor(
sampled_token_ids, dtype=torch.int32, device=device
)
sampled_token_ids_cpu = [
np.array([i for i in seq if i != -1]) for seq in sampled_token_ids
]
sampled_token_ids_cpu = [[i for i in seq if i != -1] for seq in sampled_token_ids]
expected_next_token_ids_cpu = [1, 4, 30, 40]
expected_next_token_ids_tensor = torch.tensor(

18
tests/v1/spec_decode/test_ngram.py
View File

@@ -77,7 +77,7 @@ def test_ngram_proposer():
# No match.
token_ids_cpu = np.array([[1, 2, 3, 4, 5]])
result = get_ngram_proposer(min_n=2, max_n=2, k=2).propose(
sampled_token_ids=[np.array([0])],
sampled_token_ids=[[0]],
req_ids=["0"],
num_tokens_no_spec=np.array([len(c) for c in token_ids_cpu]),
token_ids_cpu=token_ids_cpu,
@@ -88,7 +88,7 @@ def test_ngram_proposer():
# No match for 4-gram.
token_ids_cpu = np.array([[1, 2, 3, 4, 1, 2, 3]])
result = get_ngram_proposer(min_n=4, max_n=4, k=2).propose(
sampled_token_ids=[np.array([0])],
sampled_token_ids=[[0]],
req_ids=["0"],
num_tokens_no_spec=np.array([len(c) for c in token_ids_cpu]),
token_ids_cpu=token_ids_cpu,
@@ -99,7 +99,7 @@ def test_ngram_proposer():
# No match for 4-gram but match for 3-gram.
token_ids_cpu = np.array([[1, 2, 3, 4, 1, 2, 3]])
result = get_ngram_proposer(min_n=3, max_n=4, k=2).propose(
sampled_token_ids=[np.array([0])],
sampled_token_ids=[[0]],
req_ids=["0"],
num_tokens_no_spec=np.array([len(c) for c in token_ids_cpu]),
token_ids_cpu=token_ids_cpu,
@@ -111,7 +111,7 @@ def test_ngram_proposer():
# In this case, the proposer should return the 4-gram match.
token_ids_cpu = np.array([[2, 3, 4, 5, 1, 2, 3, 4, 1, 2, 3, 4]])
result = get_ngram_proposer(min_n=3, max_n=4, k=2).propose(
sampled_token_ids=[np.array([0])],
sampled_token_ids=[[0]],
req_ids=["0"],
num_tokens_no_spec=np.array([len(c) for c in token_ids_cpu]),
token_ids_cpu=token_ids_cpu,
@@ -122,7 +122,7 @@ def test_ngram_proposer():
# Match for 2-gram and 3-gram, but not 4-gram.
token_ids_cpu = np.array([[3, 4, 5, 2, 3, 4, 1, 2, 3, 4]])
result = get_ngram_proposer(min_n=2, max_n=4, k=2).propose(
sampled_token_ids=[np.array([0])],
sampled_token_ids=[[0]],
req_ids=["0"],
num_tokens_no_spec=np.array([len(c) for c in token_ids_cpu]),
token_ids_cpu=token_ids_cpu,
@@ -133,7 +133,7 @@ def test_ngram_proposer():
# Multiple 3-gram matched, but always pick the first one.
token_ids_cpu = np.array([[1, 2, 3, 100, 1, 2, 3, 200, 1, 2, 3, 300, 1, 2, 3]])
result = get_ngram_proposer(min_n=3, max_n=3, k=2).propose(
sampled_token_ids=[np.array([0])],
sampled_token_ids=[[0]],
req_ids=["0"],
num_tokens_no_spec=np.array([len(c) for c in token_ids_cpu]),
token_ids_cpu=token_ids_cpu,
@@ -144,7 +144,7 @@ def test_ngram_proposer():
# check empty input
token_ids_cpu = np.array([[]])
result = get_ngram_proposer(min_n=2, max_n=2, k=2).propose(
sampled_token_ids=[np.array([0])],
sampled_token_ids=[[0]],
req_ids=["0"],
num_tokens_no_spec=np.array([len(c) for c in token_ids_cpu]),
token_ids_cpu=token_ids_cpu,
@@ -157,7 +157,7 @@ def test_ngram_proposer():
# second request has 3 tokens and no match. Padded with -1 for max len 5
token_ids_cpu = np.array([[1, 2, 3, 1, 2], [4, 5, 6, -1, -1]])
result = get_ngram_proposer(min_n=2, max_n=2, k=2).propose(
sampled_token_ids=[np.array([0]), np.array([1])],
sampled_token_ids=[[0], [1]],
req_ids=["0", "1"],
num_tokens_no_spec=np.array([5, 3]),
token_ids_cpu=token_ids_cpu,
@@ -181,7 +181,7 @@ def test_ngram_proposer():
input_2[:3] = [4, 5, 6]
token_ids_cpu = np.array([input_1, input_2])
result = ngram_proposer.propose(
sampled_token_ids=[np.array([0]), np.array([1])],
sampled_token_ids=[[0], [1]],
req_ids=["0", "1"],
num_tokens_no_spec=np.array([len(input_1), 3]),
token_ids_cpu=token_ids_cpu,