Files
vLLM/vllm/v1/sample/ops/penalties.py
T
Russell Bryant e489ad7a21 [Misc] Add SPDX-License-Identifier headers to python source files (#12628)
- **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>
2025-02-02 11:58:18 -08:00

62 lines
2.2 KiB
Python

# SPDX-License-Identifier: Apache-2.0
from typing import List, Set, Tuple
import torch
from vllm.model_executor.layers.utils import apply_penalties
from vllm.utils import is_pin_memory_available, make_tensor_with_pad
def apply_min_token_penalties(logits: torch.Tensor,
output_token_ids: List[List[int]],
stop_token_ids: List[Set[int]],
min_tokens: List[int]) -> None:
"""
Applies minimum token penalty by setting the logits of the stop tokens
to -inf.
"""
min_tokens_logits_to_penalize: List[Tuple[int, int]] = []
for index, min_token in enumerate(min_tokens):
if len(output_token_ids[index]) < min_token:
for stop_token_id in stop_token_ids[index]:
min_tokens_logits_to_penalize.append((index, stop_token_id))
if min_tokens_logits_to_penalize:
logits[tuple(zip(*min_tokens_logits_to_penalize))] = -float("inf")
def apply_all_penalties(
logits: torch.Tensor,
prompt_token_ids: torch.Tensor,
presence_penalties: torch.Tensor,
frequency_penalties: torch.Tensor,
repetition_penalties: torch.Tensor,
output_token_ids: List[List[int]],
) -> torch.Tensor:
"""
Applies presence, frequency and repetition penalties to the logits.
"""
_, vocab_size = logits.shape
output_tokens_t = _convert_to_tensors(output_token_ids, vocab_size,
logits.device)
return apply_penalties(logits, prompt_token_ids, output_tokens_t,
presence_penalties, frequency_penalties,
repetition_penalties)
def _convert_to_tensors(output_token_ids: List[List[int]], vocab_size: int,
device: torch.device) -> torch.Tensor:
"""
Convert the different list data structures to tensors.
"""
output_tokens_tensor = make_tensor_with_pad(
output_token_ids,
# Use the value of vocab_size as a pad since we don't have a
# token_id of this value.
pad=vocab_size,
device="cpu",
dtype=torch.int64,
pin_memory=is_pin_memory_available(),
)
return output_tokens_tensor.to(device, non_blocking=True)