Wushi Dong 1d094fd7c0 [Distributed][PP] only create embedding & lm head when necessary (#6455) ...

original title: [Distributed][Model] Rank-based Component Creation for Pipeline Parallelism Memory Optimization

2024-07-16 19:20:26 -07:00

..

adapter_commons

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

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

assets

[CI/Build] Remove "boardwalk" image asset (#6460)

2024-07-16 08:59:36 -07:00

attention

[Kernel][Attention] Separate Attention.kv_scale into k_scale and v_scale (#6081)

2024-07-16 15:31:32 -07:00

core

[BugFix][Model] Jamba - Handle aborted requests, Add tests and fix cleanup bug (#6425)

2024-07-16 01:32:55 +00:00

distributed

[misc][distributed] improve tests (#6488)

2024-07-16 17:35:52 -07:00

engine

[Misc] Log spec decode metrics (#6454)

2024-07-16 20:37:10 +00:00

entrypoints

[Frontend] Support for chat completions input in the tokenize endpoint (#5923)

2024-07-16 20:18:09 +08:00

executor

[ci][distributed] add pipeline parallel correctness test (#6410)

2024-07-16 15:44:22 -07:00

inputs

[Doc] Move guide for multimodal model and other improvements (#6168)

2024-07-06 17:18:59 +08:00

logging

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

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

lora

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

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

model_executor

[Distributed][PP] only create embedding & lm head when necessary (#6455)

2024-07-16 19:20:26 -07:00

multimodal

[Bugfix] Convert image to RGB by default (#6430)

2024-07-15 05:39:15 +00:00

platforms

[CI/Build] Enable mypy typing for remaining folders (#6268)

2024-07-10 22:15:55 +08:00

prompt_adapter

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

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

spec_decode

[Speculative Decoding] Enabling bonus token in speculative decoding for KV cache based models (#5765)

2024-07-10 16:02:47 -07:00

transformers_utils

[ BugFix ] Prompt Logprobs Detokenization (#6223)

2024-07-11 22:02:29 +00:00

triton_utils

[Bugfix] Add custom Triton cache manager to resolve MoE MP issue (#6140)

2024-07-15 10:12:47 -07:00

usage

[CI/Build] vLLM cache directory for images (#6444)

2024-07-15 23:12:25 -07:00

worker

[Hardware][TPU] Support MoE with Pallas GMM kernel (#6457)

2024-07-16 09:56:28 -07:00

__init__.py

[Misc] Add generated git commit hash as vllm.__commit__ (#6386)

2024-07-12 22:52:15 +00:00

_custom_ops.py

[Kernel][Attention] Separate Attention.kv_scale into k_scale and v_scale (#6081)

2024-07-16 15:31:32 -07:00

_ipex_ops.py

[Kernel][Attention] Separate Attention.kv_scale into k_scale and v_scale (#6081)

2024-07-16 15:31:32 -07:00

block.py

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

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

config.py

[ROCm][AMD] unify CUDA_VISIBLE_DEVICES usage in cuda/rocm (#6352)

2024-07-11 21:30:46 -07:00

envs.py

[CI/Build] vLLM cache directory for images (#6444)

2024-07-15 23:12:25 -07:00

logger.py

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

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

outputs.py

[Core] Optimize block_manager_v2 vs block_manager_v1 (to make V2 default) (#5602)

2024-07-01 20:10:37 -07:00

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

Report usage for beam search (#6404)

2024-07-14 19:37:35 -07:00

scripts.py

[Feature] vLLM CLI (#5090)

2024-07-14 15:36:43 -07:00

sequence.py

[Speculative Decoding] Enabling bonus token in speculative decoding for KV cache based models (#5765)

2024-07-10 16:02:47 -07:00

tracing.py

[Misc] Add OpenTelemetry support (#4687)

2024-06-19 01:17:03 +09:00

utils.py

[ROCm][AMD] unify CUDA_VISIBLE_DEVICES usage in cuda/rocm (#6352)

2024-07-11 21:30:46 -07:00

version.py

bump version to v0.5.2 (#6433)

2024-07-15 17:27:40 +00:00