Ricardo Lu beac8dd461 fix: don't skip first special token. (#1497)

2023-10-29 04:26:36 -07:00

..

core

Fix type hints (#1427)

2023-10-20 08:50:47 -07:00

engine

Support SqueezeLLM (#1326)

2023-10-21 23:14:59 -07:00

entrypoints

API server support ipv4 / ipv6 dualstack (#1288)

2023-10-07 15:15:54 -07:00

model_executor

Add rope_scaling to Aquila model (#1457)

2023-10-29 04:25:21 -07:00

transformers_utils

fix: don't skip first special token. (#1497)

2023-10-29 04:26:36 -07:00

worker

Change scheduler & input tensor shape (#1381)

2023-10-16 17:48:42 -07:00

__init__.py

Bump up the version to v0.2.1 (#1355)

2023-10-16 12:58:57 -07:00

block.py

[Quality] Add code formatter and linter (#326)

2023-07-03 11:31:55 -07:00

config.py

Support SqueezeLLM (#1326)

2023-10-21 23:14:59 -07:00

logger.py

[Quality] Add code formatter and linter (#326)

2023-07-03 11:31:55 -07:00

outputs.py

Implement prompt logprobs & Batched topk for computing logprobs (#1328)

2023-10-16 10:56:50 -07:00

sampling_params.py

Implement prompt logprobs & Batched topk for computing logprobs (#1328)

2023-10-16 10:56:50 -07:00

sequence.py

[BugFix] Define __eq__ in SequenceGroupOutputs (#1389)

2023-10-17 01:09:44 -07:00

utils.py

Allocate more shared memory to attention kernel (#1154)

2023-09-26 22:27:13 -07:00