[Frontend] Apply each endpoint's top_logprobs cut in derender (#59518)

Signed-off-by: Yin Li <kevinli.ai.work@gmail.com>
Co-authored-by: Yin Li <kevinli.ai.work@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
This commit is contained in:
Yin Li
2026-10-15 15:04:04 +00:00
committed by GitHub
co-authored by Yin Li Cyrus Leung
parent 011fa68ca9
commit 3dcfaeb4e8
12 changed files with 409 additions and 112 deletions
@@ -139,7 +139,7 @@ def test_sentencepiece_leading_space_matches_engine():
assert [t.token for t in entry.top_logprobs] == convert_ids_list_to_tokens(
tokenizer, [spaced, bare]
)
completion = _convert_chat_logprobs_to_completion_logprobs(resolved)
completion = _convert_chat_logprobs_to_completion_logprobs(resolved, logprobs)
assert completion.top_logprobs == [{" true": -0.5, "true": -1.5}]
@@ -0,0 +1,212 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
"""generate + derender must return the same `top_logprobs` as the coupled
`/v1/chat/completions` and `/v1/completions` endpoints (#59513).
Both sides start from the same per-position engine dicts, built with the
engine's own `append_logprobs_for_next_position` and detokenized the way the
engine does, and go through the real coupled serving objects on one side and
`/inference/v1/generate` + derender on the other. The cases include a sampled
token outside the top k, where chat keeps k entries and completions k + 1; the
greedy end-to-end parity tests never produce that case.
"""
import pytest
from tests.entrypoints.openai.chat_completion.test_serving_chat import (
_build_mock_engine,
_build_serving_chat,
)
from tests.entrypoints.openai.completion.test_completion_error import (
_build_serving_completion,
)
from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
from vllm.entrypoints.openai.completion.protocol import CompletionRequest
from vllm.entrypoints.scale_out.token_in_token_out.protocol import GenerateLogProbs
from vllm.entrypoints.scale_out.token_in_token_out.serving import ServingTokens
from vllm.logprobs import append_logprobs_for_next_position
from vllm.renderers.online_derenderer import (
_chat_top_logprobs_limit,
_completion_top_logprobs_limit,
_convert_chat_logprobs_to_completion_logprobs,
_resolve_logprobs,
)
from vllm.tokenizers import get_tokenizer
from vllm.tokenizers.detokenizer_utils import convert_ids_list_to_tokens
MODEL_NAME = "hmellor/tiny-random-LlamaForCausalLM"
@pytest.fixture(scope="module")
def tokenizer():
return get_tokenizer(MODEL_NAME)
@pytest.fixture(scope="module")
def serving_chat():
return _build_serving_chat(_build_mock_engine())
@pytest.fixture(scope="module")
def serving_completion():
return _build_serving_completion(_build_mock_engine())
@pytest.fixture(scope="module")
def vocab_ids(tokenizer):
"""Ordinary word pieces (no byte-fallback tokens, which need the U+FFFD
context repair that is compared elsewhere)."""
ids = tokenizer.encode(
"the quick brown fox jumps over a lazy dog while seven cats watch "
"from an old wooden fence near the river bank",
add_special_tokens=False,
)
pieces = tokenizer.convert_ids_to_tokens(ids)
return list(dict.fromkeys(i for i, p in zip(ids, pieces) if "<0x" not in p))
def _positions(tokenizer, vocab_ids, k, sampled_ranks):
"""Engine output for one completion: per position the sampled id and its
dict (sampled first, then ranks 1..k), with decoded tokens as the engine
fills them. k = -1 returns every candidate, as for the whole vocabulary."""
token_ids, dicts = [], []
for pos, sampled_rank in enumerate(sampled_ranks):
n_top = max(k, sampled_rank) if k != -1 else len(vocab_ids) - 1
ranked = [vocab_ids[(pos + j) % len(vocab_ids)] for j in range(n_top + 1)]
sampled = ranked[sampled_rank - 1]
top = ranked[: len(ranked) - 1] if k == -1 else ranked[:k]
ids = [sampled, *top]
logprobs = [-0.25 * sampled_rank] + [-0.25 * (r + 1) for r in range(len(top))]
per_position: list = []
append_logprobs_for_next_position(
per_position,
ids,
logprobs,
convert_ids_list_to_tokens(tokenizer, ids),
sampled_rank,
len(top),
)
token_ids.append(sampled)
dicts.append(per_position[0])
return token_ids, dicts
def _generate(token_ids, dicts) -> GenerateLogProbs:
out = ServingTokens._create_tokens_logprobs(
None, token_ids=token_ids, top_logprobs=dicts
)
# Over the wire, as a derender client would send it back.
return GenerateLogProbs.model_validate_json(out.model_dump_json())
# Sampled token rank per position: top-1, inside the top k, outside it.
RANKS = [1, 2, 1, 7, 3, 9, 1]
@pytest.mark.parametrize("k", [0, 1, 2, 5, -1])
def test_chat_derender_matches_coupled_chat(tokenizer, vocab_ids, serving_chat, k):
token_ids, dicts = _positions(tokenizer, vocab_ids, k, RANKS)
coupled = serving_chat._create_chat_logprobs(
token_ids=token_ids,
top_logprobs=dicts,
tokenizer=tokenizer,
num_output_top_logprobs=k,
)
request = ChatCompletionRequest(
model=MODEL_NAME,
messages=[{"role": "user", "content": "hi"}],
logprobs=True,
top_logprobs=k,
)
derendered = _resolve_logprobs(
_generate(token_ids, dicts),
tokenizer,
top_limit=_chat_top_logprobs_limit(request),
)
assert derendered.model_dump() == coupled.model_dump()
@pytest.mark.parametrize("k", [0, 1, 2, 5, -1])
def test_completion_derender_matches_coupled_completion(
tokenizer, vocab_ids, serving_completion, k
):
token_ids, dicts = _positions(tokenizer, vocab_ids, k, RANKS)
coupled = serving_completion._create_completion_logprobs(
token_ids=token_ids,
top_logprobs=dicts,
num_output_top_logprobs=k,
tokenizer=tokenizer,
)
request = CompletionRequest(model=MODEL_NAME, prompt="hi", logprobs=k)
generated = _generate(token_ids, dicts)
derendered = _convert_chat_logprobs_to_completion_logprobs(
_resolve_logprobs(
generated,
tokenizer,
top_limit=_completion_top_logprobs_limit(request),
),
generated,
)
assert derendered.model_dump() == coupled.model_dump()
if k > 0:
# The case #59513 is about: completions keeps k + 1 entries when the
# sampled token is outside the top k.
outside = [i for i, r in enumerate(RANKS) if r > k]
assert all(len(derendered.top_logprobs[i]) == k + 1 for i in outside)
if k == -1:
# /v1/completions returns every candidate for logprobs=-1 (#55717).
assert [len(top) for top in derendered.top_logprobs] == [len(d) for d in dicts]
@pytest.mark.parametrize(
"top_limit",
[
_chat_top_logprobs_limit(None),
# A request that does not ask for logprobs says nothing about the cut.
_chat_top_logprobs_limit(
ChatCompletionRequest(
model=MODEL_NAME, messages=[{"role": "user", "content": "hi"}]
)
),
_completion_top_logprobs_limit(None),
_completion_top_logprobs_limit(
CompletionRequest(model=MODEL_NAME, prompt="hi")
),
],
)
def test_without_a_logprobs_request_derender_keeps_every_candidate(
tokenizer, vocab_ids, top_limit
):
token_ids, dicts = _positions(tokenizer, vocab_ids, 2, RANKS)
derendered = _resolve_logprobs(
_generate(token_ids, dicts), tokenizer, top_limit=top_limit
)
assert [len(e.top_logprobs) for e in derendered.content] == [len(d) for d in dicts]
@pytest.mark.parametrize("k", [-1, 0, 2])
def test_completion_position_without_logprobs_stays_none(
tokenizer, vocab_ids, serving_completion, k
):
"""A position the engine returned no logprobs for is `None` in
`/v1/completions`, not `{}`; derender keeps it that way."""
token_ids, dicts = _positions(tokenizer, vocab_ids, k, RANKS)
dicts[3] = None
coupled = serving_completion._create_completion_logprobs(
token_ids=token_ids,
top_logprobs=dicts,
num_output_top_logprobs=k,
tokenizer=tokenizer,
)
request = CompletionRequest(model=MODEL_NAME, prompt="hi", logprobs=k)
generated = _generate(token_ids, dicts)
derendered = _convert_chat_logprobs_to_completion_logprobs(
_resolve_logprobs(
generated,
tokenizer,
top_limit=_completion_top_logprobs_limit(request),
),
generated,
)
assert derendered.top_logprobs == coupled.top_logprobs
assert derendered.top_logprobs[3] is None
@@ -14,11 +14,11 @@ from vllm.logprobs import Logprob
def test_top_logprobs_alternatives_have_own_token_ids():
"""Each top_logprobs alternative must carry its own integer token id."""
# Engine dict at logprobs=2 with the sampled token 262 also top-1.
result = ServingTokens._create_tokens_logprobs(
None,
token_ids=[262],
top_logprobs=[{262: Logprob(-0.1), 257: Logprob(-1.2), 428: Logprob(-2.3)}],
num_output_top_logprobs=2,
top_logprobs=[{262: Logprob(-0.1), 257: Logprob(-1.2)}],
)
token_ids = {e.token_id for e in result.content[0].top_logprobs}
assert token_ids == {262, 257}, f"got {token_ids}"
@@ -32,7 +32,6 @@ def test_sampled_entry_carries_token_id_and_rank():
top_logprobs=[
{262: Logprob(-0.1, rank=1), 257: Logprob(-1.2, rank=2)},
],
num_output_top_logprobs=2,
)
entry = result.content[0]
assert entry.token_id == 262
@@ -50,7 +49,6 @@ def test_sampled_token_absent_from_topk_uses_sentinel():
None,
token_ids=[5],
top_logprobs=[{7: Logprob(-0.9)}],
num_output_top_logprobs=1,
)
entry = result.content[0]
assert entry.token_id == 5
@@ -60,14 +58,13 @@ def test_sampled_token_absent_from_topk_uses_sentinel():
def test_logprobs_zero_emits_sampled_token():
"""logprobs=0 must still emit 1 entry (the sampled token)."""
"""logprobs=0: the engine returns only the sampled token, and it is kept."""
result = ServingTokens._create_tokens_logprobs(
None,
token_ids=[7],
top_logprobs=[{7: Logprob(-0.9), 8: Logprob(-1.1)}],
num_output_top_logprobs=0,
top_logprobs=[{7: Logprob(-0.9)}],
)
assert len(result.content[0].top_logprobs) == 1
assert [t.token_id for t in result.content[0].top_logprobs] == [7]
def test_logprobs_minus_one_emits_all_tokens():
@@ -75,7 +72,6 @@ def test_logprobs_minus_one_emits_all_tokens():
None,
token_ids=[7],
top_logprobs=[{7: Logprob(-0.9), 8: Logprob(-1.1)}],
num_output_top_logprobs=-1,
)
assert len(result.content[0].top_logprobs) == 2
@@ -86,7 +82,6 @@ def test_text_logprobs_without_tokenizer_are_placeholders_without_bytes():
None,
token_ids=[7],
top_logprobs=[{7: Logprob(-0.9), 8: Logprob(-1.1)}],
num_output_top_logprobs=2,
)
entry = result.content[0]
assert entry.token == "token_id:7"
@@ -102,7 +97,6 @@ def test_resolved_logprobs_use_engine_decoded_tokens_and_bytes():
top_logprobs=[
{7: Logprob(-0.9, decoded_token="é"), 8: Logprob(-1.1, decoded_token="e")}
],
num_output_top_logprobs=2,
tokenizer=tokenizer,
)
entry = result.content[0]
@@ -121,7 +115,6 @@ def test_resolved_logprobs_decode_tokens_the_engine_did_not():
None,
token_ids=[7, 9],
top_logprobs=[{7: Logprob(-0.9)}, None],
num_output_top_logprobs=1,
tokenizer=tokenizer,
)
assert [e.token for e in result.content] == ["<7>", "<9>"]
@@ -130,9 +123,9 @@ def test_resolved_logprobs_decode_tokens_the_engine_did_not():
def test_sampled_token_outside_topk_comes_first():
"""The engine puts the sampled token first, then ranks 1..k. When the
sampled token is outside the top k it takes one of the k slots, so rank k
is left out (same as the OpenAI endpoints)."""
"""The engine puts the sampled token first, then ranks 1..k. Generate keeps
all k + 1 candidates when the sampled token is outside the top k; derender
applies each endpoint's cut (#59513)."""
result = ServingTokens._create_tokens_logprobs(
None,
token_ids=[50],
@@ -143,9 +136,8 @@ def test_sampled_token_outside_topk_comes_first():
20: Logprob(-1.0, rank=2),
}
],
num_output_top_logprobs=2,
)
assert [t.rank for t in result.content[0].top_logprobs] == [5, 1]
assert [t.rank for t in result.content[0].top_logprobs] == [5, 1, 2]
def test_logprob_is_required_on_the_wire():
@@ -160,7 +152,6 @@ def test_rank_zero_from_a_nan_logprob_is_none():
None,
token_ids=[7],
top_logprobs=[{7: Logprob(float("nan"), rank=0), 8: Logprob(-0.2, rank=1)}],
num_output_top_logprobs=1,
)
entry = result.content[0]
assert entry.rank is None
@@ -176,7 +167,6 @@ def test_text_logprobs_clamp_a_nan_logprob():
None,
token_ids=[7],
top_logprobs=[{7: Logprob(float("nan"), rank=0, decoded_token="a")}],
num_output_top_logprobs=1,
tokenizer=MagicMock(),
)
entry = result.content[0]