[Core][V1] Support trace_decode_token_ids for deterministic decode replay (#46701)

Signed-off-by: ianzxliu <ianzxliu@tencent.com>
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Signed-off-by: Zhixia Liu <liuzhixia.nju@gmail.com>
Co-authored-by: ianzxliu <ianzxliu@tencent.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
This commit is contained in:
Zhixia Liu
2026-08-20 15:12:43 +08:00
committed by GitHub
co-authored by ianzxliu Claude aoshen02 Codex Nick Hill
parent 754e1c3de4
commit a1c5b1fd9f
13 changed files with 931 additions and 9 deletions
+14
View File
@@ -26,6 +26,7 @@ from vllm.v1.worker.gpu.sample.output import SamplerOutput, SamplingMaskTensors
from vllm.v1.worker.gpu.sample.penalties import PenaltiesState
from vllm.v1.worker.gpu.sample.states import NO_LOGPROBS, SamplingStates
from vllm.v1.worker.gpu.sample.thinking_budget import ThinkingBudgetState
from vllm.v1.worker.gpu.sample.trace_replay import TraceReplayState
from vllm.v1.worker.gpu.states import RequestState
@@ -39,6 +40,7 @@ class Sampler:
logprobs_mode: LogprobsMode = "raw_logprobs",
num_speculative_tokens: int = 1,
use_fp64_gumbel: bool = False,
enable_trace_replay: bool = False,
reasoning_config: ReasoningConfig | None = None,
return_sampling_mask: bool = False,
):
@@ -53,6 +55,9 @@ class Sampler:
self.bad_words_state = BadWordsState(req_states)
self.logprob_token_ids_state = LogprobTokenIdsState(max_num_reqs, device)
self.thinking_budget_state = ThinkingBudgetState(req_states, reasoning_config)
self.trace_replay_state = (
TraceReplayState(req_states) if enable_trace_replay else None
)
self.needs_logits_processing = np.zeros(max_num_reqs, dtype=bool)
self.num_speculative_tokens = num_speculative_tokens
self.return_sampling_mask = return_sampling_mask
@@ -69,6 +74,8 @@ class Sampler:
self.bad_words_state.add_request(req_idx, sampling_params)
self.logprob_token_ids_state.add_request(req_idx, sampling_params)
self.thinking_budget_state.add_request(req_idx, sampling_params)
if self.trace_replay_state is not None:
self.trace_replay_state.add_request(req_idx, sampling_params)
states = self.sampling_states
temperature = states.temperature.np[req_idx]
@@ -93,6 +100,8 @@ class Sampler:
self.bad_words_state.apply_staged_writes()
self.logprob_token_ids_state.apply_staged_writes()
self.thinking_budget_state.apply_staged_writes()
if self.trace_replay_state is not None:
self.trace_replay_state.apply_staged_writes()
def __call__(
self,
@@ -128,6 +137,11 @@ class Sampler:
return_logprobs=return_logprobs,
)
if self.trace_replay_state is not None:
# Overwrite sampled tokens with the replay trace up-front so that
# computed logprobs reflect the real distribution of the forced token.
self.trace_replay_state.apply_trace(sampled, idx_mapping)
if return_logprobs:
if self.logprobs_mode in PROCESSED_LOGPROBS_MODES:
logits = processed_logits
+113
View File
@@ -0,0 +1,113 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
import torch
from vllm.sampling_params import SamplingParams
from vllm.triton_utils import tl, triton
from vllm.v1.worker.gpu.buffer_utils import StagedWriteTensor, UvaBackedTensor
from vllm.v1.worker.gpu.states import RequestState
class TraceReplayState:
"""Per-request state for inference trace-replay.
When a request carries ``SamplingParams.trace_decode_token_ids``, the
sampler overwrites the sampled token at each decode step with the
predetermined trace token, while real logprobs and ranks are still computed
from the unmodified logit distribution. The replay step for a request is
derived entirely from GPU state (``total_len - prompt_len``), so no CPU
synchronization or async placeholder handling is needed.
"""
def __init__(self, req_states: RequestState):
self.max_num_reqs = req_states.max_num_reqs
self.device = req_states.device
self.req_states = req_states
self.trace_token_ids = StagedWriteTensor(
(self.max_num_reqs, req_states.max_model_len),
dtype=torch.int32,
device=self.device,
uva_instead_of_gpu=True,
)
self.trace_len = UvaBackedTensor(self.max_num_reqs, dtype=torch.int32)
def add_request(self, req_idx: int, sampling_params: SamplingParams) -> None:
trace = sampling_params.trace_decode_token_ids
if trace is not None:
self.trace_len.np[req_idx] = len(trace)
self.trace_token_ids.stage_write(req_idx, 0, trace)
else:
self.trace_len.np[req_idx] = 0
def apply_staged_writes(self) -> None:
self.trace_len.copy_to_uva()
self.trace_token_ids.apply_write()
def apply_trace(
self,
sampled: torch.Tensor,
idx_mapping: torch.Tensor,
) -> None:
apply_trace_tokens(
sampled,
idx_mapping,
self.trace_token_ids.gpu,
self.trace_len.gpu,
self.req_states.total_len.gpu,
self.req_states.prompt_len.gpu,
)
@triton.jit
def _trace_replay_kernel(
sampled_ptr, # [num_reqs], int64, mutated in place
idx_mapping_ptr, # [num_reqs] batch_idx -> req_state_idx
trace_token_ids_ptr, # [max_num_reqs, max_model_len], int32
trace_token_ids_stride,
trace_len_ptr, # [max_num_reqs], int32
total_len_ptr, # [max_num_reqs], int32
prompt_len_ptr, # [max_num_reqs], int32
):
batch_idx = tl.program_id(0)
req_state_idx = tl.load(idx_mapping_ptr + batch_idx)
if req_state_idx < 0:
return
trace_len = tl.load(trace_len_ptr + req_state_idx)
if trace_len <= 0:
return
# The token being sampled now is output token number
# (total_len - prompt_len): total_len reflects tokens committed through the
# previous step (post_update runs after sampling).
step = tl.load(total_len_ptr + req_state_idx) - tl.load(
prompt_len_ptr + req_state_idx
)
if step < 0 or step >= trace_len:
return
token_id = tl.load(
trace_token_ids_ptr + req_state_idx * trace_token_ids_stride + step
)
tl.store(sampled_ptr + batch_idx, token_id.to(tl.int64))
def apply_trace_tokens(
sampled: torch.Tensor,
idx_mapping: torch.Tensor,
trace_token_ids: torch.Tensor,
trace_len: torch.Tensor,
total_len: torch.Tensor,
prompt_len: torch.Tensor,
) -> None:
"""Overwrite ``sampled`` in place with trace tokens for the current step."""
num_reqs = idx_mapping.shape[0]
_trace_replay_kernel[(num_reqs,)](
sampled,
idx_mapping,
trace_token_ids,
trace_token_ids.stride(0),
trace_len,
total_len,
prompt_len,
)