wangjing 8ba49a7723 [gpt-oss] Add gpt-oss bf16 support

2025-08-13 21:25:57 +08:00

adapter_commons

init

2025-08-13 19:46:19 +08:00

assets

init

2025-08-13 19:46:19 +08:00

attention

[gpt-oss] Add gpt-oss bf16 support

2025-08-13 21:25:57 +08:00

benchmarks

init

2025-08-13 19:46:19 +08:00

compilation

init

2025-08-13 19:46:19 +08:00

core

init

2025-08-13 19:46:19 +08:00

device_allocator

init

2025-08-13 19:46:19 +08:00

distributed

init

2025-08-13 19:46:19 +08:00

engine

init

2025-08-13 19:46:19 +08:00

entrypoints

init

2025-08-13 19:46:19 +08:00

executor

init

2025-08-13 19:46:19 +08:00

inputs

init

2025-08-13 19:46:19 +08:00

logging_utils

init

2025-08-13 19:46:19 +08:00

lora

init

2025-08-13 19:46:19 +08:00

model_executor

[gpt-oss] Add gpt-oss bf16 support

2025-08-13 21:25:57 +08:00

multimodal

init

2025-08-13 19:46:19 +08:00

platforms

[gpt-oss] Add gpt-oss bf16 support

2025-08-13 21:25:57 +08:00

plugins

init

2025-08-13 19:46:19 +08:00

profiler

init

2025-08-13 19:46:19 +08:00

prompt_adapter

init

2025-08-13 19:46:19 +08:00

reasoning

init

2025-08-13 19:46:19 +08:00

spec_decode

init

2025-08-13 19:46:19 +08:00

third_party

init

2025-08-13 19:46:19 +08:00

transformers_utils

[gpt-oss] Add gpt-oss bf16 support

2025-08-13 21:25:57 +08:00

triton_utils

init

2025-08-13 19:46:19 +08:00

usage

init

2025-08-13 19:46:19 +08:00

v1

[gpt-oss] Add gpt-oss bf16 support

2025-08-13 21:25:57 +08:00

vllm_flash_attn

init

2025-08-13 19:46:19 +08:00

worker

init

2025-08-13 19:46:19 +08:00

__init__.py

init

2025-08-13 19:46:19 +08:00

_C.abi3.so

init

2025-08-13 19:46:19 +08:00

_custom_ops.py

init

2025-08-13 19:46:19 +08:00

_ipex_ops.py

init

2025-08-13 19:46:19 +08:00

_moe_C.abi3.so

init

2025-08-13 19:46:19 +08:00

_release_info.txt

init

2025-08-13 19:46:19 +08:00

.gitignore

init

2025-08-13 19:46:19 +08:00

beam_search.py

init

2025-08-13 19:46:19 +08:00

collect_env.py

init

2025-08-13 19:46:19 +08:00

config.py

init

2025-08-13 19:46:19 +08:00

connections.py

init

2025-08-13 19:46:19 +08:00

cumem_allocator.abi3.so

init

2025-08-13 19:46:19 +08:00

env_override.py

init

2025-08-13 19:46:19 +08:00

envs.py

init

2025-08-13 19:46:19 +08:00

forward_context.py

init

2025-08-13 19:46:19 +08:00

jsontree.py

init

2025-08-13 19:46:19 +08:00

logger.py

init

2025-08-13 19:46:19 +08:00

logits_process.py

init

2025-08-13 19:46:19 +08:00

outputs.py

init

2025-08-13 19:46:19 +08:00

pooling_params.py

init

2025-08-13 19:46:19 +08:00

py.typed

init

2025-08-13 19:46:19 +08:00

sampling_params.py

init

2025-08-13 19:46:19 +08:00

scalar_type.py

init

2025-08-13 19:46:19 +08:00

scripts.py

init

2025-08-13 19:46:19 +08:00

sequence.py

init

2025-08-13 19:46:19 +08:00

test_utils.py

init

2025-08-13 19:46:19 +08:00

tracing.py

init

2025-08-13 19:46:19 +08:00

utils.py

init

2025-08-13 19:46:19 +08:00

version.py

init

2025-08-13 19:46:19 +08:00

Description

运行于沐曦曦云C系列算力卡的【文本生成】引擎 vLLM 特制优化版本，基于 transformer 架构，支持 gpt-oss 等最新流行模型

vllm

64 MiB

Languages

Python 100%