Cyrus Leung e0191a95d8 [0/N] Rename MultiModalInputs to MultiModalKwargs (#10040) ... Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>		2024-11-09 11:31:02 +08:00
..
__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	[Feature] [Spec decode]: Combine chunked prefill with speculative decoding (#9291)	2024-11-07 08:15:14 -08:00
draft_model_runner.py	[0/N] Rename MultiModalInputs to MultiModalKwargs (#10040)	2024-11-09 11:31:02 +08:00
interfaces.py	[Spec Decode] (1/2) Remove batch expansion (#8839)	2024-10-01 16:04:42 -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
mqa_scorer.py	[Feature] [Spec decode]: Combine chunked prefill with speculative decoding (#9291)	2024-11-07 08:15:14 -08:00
multi_step_worker.py	[Bugfix][SpecDecode] kv corruption with bonus tokens in spec decode (#9730)	2024-11-06 01:45:45 +00:00
ngram_worker.py	[2/N] executor pass the complete config to worker/modelrunner (#9938)	2024-11-02 07:35:05 -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	[Feature] [Spec decode]: Combine chunked prefill with speculative decoding (#9291)	2024-11-07 08:15:14 -08:00
target_model_runner.py	[2/N] executor pass the complete config to worker/modelrunner (#9938)	2024-11-02 07:35:05 -07:00
top1_proposer.py	[Feature] [Spec decode]: Combine chunked prefill with speculative decoding (#9291)	2024-11-07 08:15:14 -08:00
util.py	[Core][Bugfix] Support prompt_logprobs returned with speculative decoding (#8047)	2024-09-24 17:29:56 -07:00