GitLab

Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
Co-authored-by: Nick Hill <nhill@redhat.com>

Signed-off-by: Roger Wang <ywang@roblox.com>

Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>

Signed-off-by: Nick Hill <nhill@redhat.com>

Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Co-authored-by: Russell Bryant <rbryant@redhat.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Nick Hill <nhill@redhat.com>

Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>

Signed-off-by: Jun Duan <jun.duan.phd@outlook.com>

Signed-off-by: Chen Zhang <zhangch99@outlook.com>

Signed-off-by: Xiongfei Wei <isaacwxf23@gmail.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

Signed-off-by: Yang Chen <yangche@fb.com>

Signed-off-by: youkaichao <youkaichao@gmail.com>

Signed-off-by: youkaichao <youkaichao@gmail.com>

Signed-off-by: Jennifer Zhao <7443418+JenZhao@users.noreply.github.com>
Co-authored-by: Roger Wang <ywang@roblox.com>

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

Signed-off-by: Nick Hill <nhill@redhat.com>

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

Signed-off-by: Cody Yu <hao.yu.cody@gmail.com>

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

Signed-off-by: LiuXiaoxuanPKU <lilyliupku@gmail.com>

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

[Bugfix][V1] GPUModelRunner._update_states should return True when there is a finished request in batch (#13126)

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

This PR is adding support for sample logprobs & prompt logprobs to vLLM v1.

New behavior:

- During model execution, model runner computes sample logprobs (if user-provided logprobs setting is not None) and prompt logprobs (if user-provided prompt_logprobs setting is not None). For both sample and prompt logprobs, the engine core returns 3 vectors: token ids, token logprob values, token ranks. Ranks reflect tokens' 1-indexed positions in the vocabulary vector after sorting the vocabulary by log probability in descending order.
- In scheduler.update_from_output(), sample and prompt logprobs are incorporated into the EngineCoreOutput data structure which is transferred to the engine client. If multiprocessing is enabled, then sample and prompt logprobs will be (de)serialized when the EngineCoreOutput data structure is (de)serialized.
- During output processing, the LogprobsProcessor transforms the triplet of token ids, token logprobs values, and token ranks into the OpenAI-compatible List[Dict[token id,Logprob]] format (for sample and prompt logprobs respectively.)
- Each Logprob instance (whether sample- or prompt-) consists of a token's log-probability, rank, and detokenized string representation. Note that logprob detokenization is handled by the LogprobsProcessor not the detokenizer.
Signed-off-by: Andrew Feldman <afeldman@neuralmagic.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Co-authored-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Co-authored-by: Nick Hill <nhill@redhat.com>

Signed-off-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>