Siyuan Liu 0fa14907da

[TPU] Add Load-time W8A16 quantization for TPU Backend (#7005)

2024-08-08 18:35:49 -07:00

..

adapter_commons

[mypy] Enable following imports for some directories (#6681)

2024-07-31 10:38:03 +08:00

assets

[Misc] Manage HTTP connections in one place (#6600)

2024-07-22 21:32:02 -07:00

attention

[Kernel] Fix Flashinfer Correctness (#7284)

2024-08-07 16:26:52 -07:00

core

[Bugfix][fast] Fix the get_num_blocks_touched logic (#6849)

2024-08-08 10:43:30 -07:00

distributed

[distributed][misc] add specialized method for cuda platform (#7249)

2024-08-07 08:54:52 -07:00

engine

[Frontend] Kill the server on engine death (#6594)

2024-08-08 09:47:48 -07:00

entrypoints

[Frontend] Kill the server on engine death (#6594)

2024-08-08 09:47:48 -07:00

executor

[Misc] Revive to use loopback address for driver IP (#7091)

2024-08-02 15:50:00 -07:00

inputs

[Core] Subclass ModelRunner to support cross-attention & encoder sequences (towards eventual encoder/decoder model support) (#4942)

2024-08-06 16:51:47 -04:00

logging

[MISC] Rework logger to enable pythonic custom logging configuration to be provided (#4273)

2024-05-01 17:34:40 -07:00

lora

[Bugfix] Fix LoRA with PP (#7292)

2024-08-08 00:02:27 -07:00

model_executor

[TPU] Add Load-time W8A16 quantization for TPU Backend (#7005)

2024-08-08 18:35:49 -07:00

multimodal

[Model] Add multi-image support for minicpmv (#7122)

2024-08-05 09:23:17 +08:00

platforms

[distributed][misc] add specialized method for cuda platform (#7249)

2024-08-07 08:54:52 -07:00

prompt_adapter

[CORE] Adding support for insertion of soft-tuned prompts (#4645)

2024-07-09 13:26:36 -07:00

spec_decode

[SpecDecode] Support FlashInfer in DraftModelRunner (#6926)

2024-08-05 08:05:05 -07:00

transformers_utils

[Frontend] Gracefully handle missing chat template and fix CI failure (#7238)

2024-08-07 09:12:05 +00:00

triton_utils

[Kernel][RFC] Refactor the punica kernel based on Triton (#5036)

2024-07-31 17:12:24 -07:00

usage

[Misc] Manage HTTP connections in one place (#6600)

2024-07-22 21:32:02 -07:00

worker

[Core] Subclass ModelRunner to support cross-attention & encoder sequences (towards eventual encoder/decoder model support) (#4942)

2024-08-06 16:51:47 -04:00

__init__.py

[Frontend] Refactor prompt processing (#4028)

2024-07-22 10:13:53 -07:00

_core_ext.py

[Misc] Disambiguate quantized types via a new ScalarType (#6396)

2024-08-02 13:51:58 -07:00

_custom_ops.py

[Kernel] Add per-tensor and per-token AZP epilogues (#5941)

2024-08-06 18:17:08 +00:00

_ipex_ops.py

[mypy] Enable following imports for some directories (#6681)

2024-07-31 10:38:03 +08:00

block.py

[core][misc] remove logical block (#5882)

2024-06-27 13:34:55 -07:00

config.py

[TPU] Add Load-time W8A16 quantization for TPU Backend (#7005)

2024-08-08 18:35:49 -07:00

connections.py

[core][distributed] fix zmq hang (#6759)

2024-07-24 17:37:12 -07:00

envs.py

[Frontend] Kill the server on engine death (#6594)

2024-08-08 09:47:48 -07:00

logger.py

[Misc] add logging level env var (#5045)

2024-05-24 23:49:49 -07:00

outputs.py

[Core] Subclass ModelRunner to support cross-attention & encoder sequences (towards eventual encoder/decoder model support) (#4942)

2024-08-06 16:51:47 -04:00

pooling_params.py

[Model][Misc] Add e5-mistral-7b-instruct and Embedding API (#3734)

2024-05-11 11:30:37 -07:00

py.typed

Add py.typed so consumers of vLLM can get type checking (#1509)

2023-10-30 14:50:47 -07:00

sampling_params.py

[BUGFIX]: top_k is expected to be an integer. (#7227)

2024-08-07 00:32:16 -07:00

scalar_type.py

[Misc] Disambiguate quantized types via a new ScalarType (#6396)

2024-08-02 13:51:58 -07:00

scripts.py

Fixes typo in function name (#7275)

2024-08-07 09:29:27 -07:00

sequence.py

[Core] Subclass ModelRunner to support cross-attention & encoder sequences (towards eventual encoder/decoder model support) (#4942)

2024-08-06 16:51:47 -04:00

tracing.py

[ Frontend ] Multiprocessing for OpenAI Server with zeromq (#6883)

2024-08-02 18:27:28 -07:00

utils.py

[FrontEnd] Make merge_async_iterators is_cancelled arg optional (#7282)

2024-08-07 13:35:14 -07:00

version.py

bump version to v0.5.4 (#7139)

2024-08-05 14:39:48 -07:00