wenyujin333 bd43973522

[Kernel] Tune Qwen2MoE kernel configurations with tp2,4 (#5497) ...

Tune Qwen2-57B-A14B configs based on #4921

Throughput Performance
command: python benchmarks/benchmark_throughput.py --model=Qwen/Qwen2-57B-A14B-Instruct --input-len 1000 --output-len 50 -tp 2

A100 GPU

benchmark	no config	w/ PR
tp=2	10.53 requests/s, 11058.17 tokens/s	12.47 requests/s, 13088.57 tokens/s
tp=4	17.77 requests/s, 18662.95 tokens/s	20.20 requests/s, 21212.32 tokens/s

2024-06-13 09:01:10 -07:00

..

attention

[Core][Distributed] code deduplication in tp&pp with coordinator(#5293)

2024-06-12 17:27:08 -07:00

core

[Bugfix] Fix typo in scheduler.py (requeset -> request) (#5470)

2024-06-12 21:59:44 +00:00

distributed

[Core][Distributed] code deduplication in tp&pp with coordinator(#5293)

2024-06-12 17:27:08 -07:00

engine

[Hardware] Initial TPU integration (#5292)

2024-06-12 11:53:03 -07:00

entrypoints

[Frontend] Add "input speed" to tqdm postfix alongside output speed (#5425)

2024-06-12 18:42:12 -04:00

executor

[Hardware] Initial TPU integration (#5292)

2024-06-12 11:53:03 -07:00

logging

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

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

lora

[Misc] Improve error message when LoRA parsing fails (#5194)

2024-06-10 19:38:49 +08:00

model_executor

[Kernel] Tune Qwen2MoE kernel configurations with tp2,4 (#5497)

2024-06-13 09:01:10 -07:00

multimodal

[Bugfix] Fix LLaVA-NeXT (#5380)

2024-06-10 15:38:47 +00:00

spec_decode

[Misc] Various simplifications and typing fixes (#5368)

2024-06-11 10:29:02 +08:00

transformers_utils

[Frontend] Customizable RoPE theta (#5197)

2024-06-11 10:42:26 -07:00

usage

[Frontend] Separate OpenAI Batch Runner usage from API Server (#4851)

2024-05-17 00:42:41 +09:00

worker

[Core][Distributed] code deduplication in tp&pp with coordinator(#5293)

2024-06-12 17:27:08 -07:00

__init__.py

Bump version to v0.5.0 (#5384)

2024-06-10 15:56:06 -07:00

_custom_ops.py

[misc] add hint for AttributeError (#5462)

2024-06-12 21:46:35 +00:00

block.py

Add Automatic Prefix Caching (#2762)

2024-03-02 00:50:01 -08:00

config.py

[Hardware] Initial TPU integration (#5292)

2024-06-12 11:53:03 -07:00

envs.py

[Hardware] Initial TPU integration (#5292)

2024-06-12 11:53:03 -07:00

inputs.py

[Bugfix] TYPE_CHECKING for MultiModalData (#5444)

2024-06-12 14:08:52 -07:00

logger.py

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

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

outputs.py

[Core] Consolidate prompt arguments to LLM engines (#4328)

2024-05-28 13:29:31 -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

[Core]: Option To Use Prompt Token Ids Inside Logits Processor (#4985)

2024-05-23 22:04:24 +00:00

sequence.py

[Core] Support image processor (#4197)

2024-06-02 22:56:41 -07:00

utils.py

[Hardware] Initial TPU integration (#5292)

2024-06-12 11:53:03 -07:00