| .. |
|
__init__.py
|
[Bugfix] Add __init__.py files for vllm/core/block/ and vllm/spec_decode/ (#3798)
|
2024-04-02 12:35:31 -07:00 |
|
batch_expansion.py
|
[Core] Logprobs support in Multi-step (#7652)
|
2024-08-29 19:19:08 -07:00 |
|
draft_model_runner.py
|
[CI/Build] Update Ruff version (#8469)
|
2024-09-18 11:00:56 +00:00 |
|
interfaces.py
|
[BUGFIX] Raise an error for no draft token case when draft_tp>1 (#6369)
|
2024-07-19 06:01:09 -07:00 |
|
medusa_worker.py
|
[Core] Logprobs support in Multi-step (#7652)
|
2024-08-29 19:19:08 -07:00 |
|
metrics.py
|
[CI/Build] Update Ruff version (#8469)
|
2024-09-18 11:00:56 +00:00 |
|
mlp_speculator_worker.py
|
[Core] Logprobs support in Multi-step (#7652)
|
2024-08-29 19:19:08 -07:00 |
|
multi_step_worker.py
|
[Core] Logprobs support in Multi-step (#7652)
|
2024-08-29 19:19:08 -07:00 |
|
ngram_worker.py
|
[Core] Logprobs support in Multi-step (#7652)
|
2024-08-29 19:19:08 -07:00 |
|
proposer_worker_base.py
|
[Core] Logprobs support in Multi-step (#7652)
|
2024-08-29 19:19:08 -07:00 |
|
smaller_tp_proposer_worker.py
|
[Core] Logprobs support in Multi-step (#7652)
|
2024-08-29 19:19:08 -07:00 |
|
spec_decode_worker.py
|
[SpecDecode][Kernel] Flashinfer Rejection Sampling (#7244)
|
2024-09-01 21:23:29 -07:00 |
|
target_model_runner.py
|
[VLM] Refactor MultiModalConfig initialization and profiling (#7530)
|
2024-08-17 13:30:55 -07:00 |
|
top1_proposer.py
|
[Core] Logprobs support in Multi-step (#7652)
|
2024-08-29 19:19:08 -07:00 |
|
util.py
|
[Core] Logprobs support in Multi-step (#7652)
|
2024-08-29 19:19:08 -07:00 |
9d104b5beb