Rui Qiao bae888cb8e

[Bugfix] Clear engine reference in AsyncEngineRPCServer (#7618) ...

Signed-off-by: Rui Qiao <ruisearch42@gmail.com>

2024-08-16 20:44:05 -07:00

..

adapter_commons

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

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

assets

[Core][VLM] Support image embeddings as input (#6613)

2024-08-12 16:16:06 +08:00

attention

[spec decode] [4/N] Move update_flash_attn_metadata to attn backend (#7571)

2024-08-16 11:41:56 -07:00

core

[Core] Fix tracking of model forward time in case of PP>1 (#7440)

2024-08-16 13:46:01 -07:00

distributed

[Bugfix] Fix custom_ar support check (#7617)

2024-08-16 19:05:49 -07:00

engine

[Core] Fix tracking of model forward time in case of PP>1 (#7440)

2024-08-16 13:46:01 -07:00

entrypoints

[Bugfix] Clear engine reference in AsyncEngineRPCServer (#7618)

2024-08-16 20:44:05 -07:00

executor

[Bugfix] update neuron for version > 0.5.0 (#7175)

2024-08-15 09:44:14 -07:00

inputs

[VLM][Core] Support profiling with multiple multi-modal inputs per prompt (#7126)

2024-08-14 17:55:42 +00:00

logging

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

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

lora

[Kernel] register punica functions as torch ops (#7591)

2024-08-16 13:59:38 -07:00

model_executor

[Model] Align nemotron config with final HF state and fix lm-eval-small (#7611)

2024-08-16 15:56:34 -07:00

multimodal

[VLM][Core] Support profiling with multiple multi-modal inputs per prompt (#7126)

2024-08-14 17:55:42 +00:00

platforms

[hardware] unify usage of is_tpu to current_platform.is_tpu() (#7102)

2024-08-13 00:16:42 -07:00

plugins

[misc][plugin] add plugin system implementation (#7426)

2024-08-13 16:24:17 -07:00

prompt_adapter

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

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

spec_decode

[spec decode] [4/N] Move update_flash_attn_metadata to attn backend (#7571)

2024-08-16 11:41:56 -07:00

transformers_utils

[Model] Align nemotron config with final HF state and fix lm-eval-small (#7611)

2024-08-16 15:56:34 -07:00

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] Fix tracking of model forward time in case of PP>1 (#7440)

2024-08-16 13:46:01 -07:00

__init__.py

[Frontend] Refactor prompt processing (#4028)

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

_core_ext.py

[Kernel][Misc] dynamo support for ScalarType (#7594)

2024-08-16 13:59:49 -07:00

_custom_ops.py

[Kernel] fix types used in aqlm and ggml kernels to support dynamo (#7596)

2024-08-16 14:00:11 -07:00

_ipex_ops.py

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

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

block.py

[Performance] Optimize e2e overheads: Reduce python allocations (#7162)

2024-08-08 21:34:28 -07:00

config.py

[Kernel] W8A16 Int8 inside FusedMoE (#7415)

2024-08-16 10:06:51 -07:00

connections.py

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

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

envs.py

[Bugfix][TPU] Correct env variable for XLA cache path (#7544)

2024-08-15 00:02:29 -07:00

logger.py

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

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

outputs.py

[Bugfix] Fix weight loading for Chameleon when TP>1 (#7410)

2024-08-13 05:33:41 +00:00

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

Fix empty output when temp is too low (#2937)

2024-08-14 05:31:44 +00:00

scalar_type.py

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

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

scripts.py

[Frontend] Disallow passing model as both argument and option (#7347)

2024-08-12 12:58:34 +00:00

sequence.py

[core] [3/N] multi-step args and sequence.py (#7452)

2024-08-14 12:32:45 -07:00

tracing.py

[Core] Add span metrics for model_forward, scheduler and sampler time (#7089)

2024-08-09 13:55:13 -07:00

utils.py

[VLM][Core] Support profiling with multiple multi-modal inputs per prompt (#7126)

2024-08-14 17:55:42 +00:00

version.py

bump version to v0.5.4 (#7139)

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