Ying Zhong 9f1710f1ac

Fix mla prefill context performance (#13897) ...

Signed-off-by: ZhongYingMatrix <zhongyingmatrix@gmail.com>

2025-03-06 09:35:49 -08:00

..

adapter_commons

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

assets

[Frontend] Add /v1/audio/transcriptions OpenAI API endpoint (#12909)

2025-02-13 07:23:45 -08:00

attention

Fix mla prefill context performance (#13897)

2025-03-06 09:35:49 -08:00

compilation

[V1] EP/TP MoE + DP Attention (#13931)

2025-03-04 21:27:26 -08:00

core

[Bugfix][Core] fix abort_seq_group and memory leak when n>1 (#14326)

2025-03-06 23:59:32 +08:00

device_allocator

[sleep mode] error out with expandable_segments (#14189)

2025-03-04 18:54:19 +08:00

distributed

[Security] Serialize using safetensors instead of pickle in Mooncake Pipe (#14228)

2025-03-04 21:10:32 +00:00

engine

[RLHF] use worker_extension_cls for compatibility with V0 and V1 (#14185)

2025-03-07 00:32:46 +08:00

entrypoints

Reinstate best_of for V0 (#14356)

2025-03-06 08:34:22 -08:00

executor

[misc] Mention ray list nodes command to troubleshoot ray issues (#14318)

2025-03-06 02:00:36 +00:00

inputs

[Core] Don't use cache during multi-modal profiling (#14336)

2025-03-06 08:03:31 -08:00

logging_utils

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

lora

[LoRA] Remove linear hack outside transformers backend (#14177)

2025-03-05 15:06:28 +00:00

model_executor

[Core] Optimizing cross-attention QKVParallelLinear computation (#12325)

2025-03-06 09:37:26 +00:00

multimodal

[Core] Don't use cache during multi-modal profiling (#14336)

2025-03-06 08:03:31 -08:00

platforms

[platforms] improve rocm debugging info (#14257)

2025-03-04 21:32:18 -08:00

plugins

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

profiler

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

prompt_adapter

[Misc] set single whitespace between log sentences (#13771)

2025-02-25 10:26:12 +08:00

spec_decode

[Bugfix] Fix DeepSeek MTP crash when using TP1ModelRunner with CUDA graph due to shape mismatch (#14237)

2025-03-05 22:22:40 +00:00

third_party

[core] port pynvml into vllm codebase (#12963)

2025-02-09 15:00:00 +08:00

transformers_utils

[Bugfix] Add file lock for ModelScope download (#14060)

2025-03-01 06:10:28 +00:00

triton_utils

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

usage

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

v1

Fix mla prefill context performance (#13897)

2025-03-06 09:35:49 -08:00

vllm_flash_attn

[ci][build] fix vllm-flash-attn (#8699)

2024-09-21 23:24:58 -07:00

worker

[RLHF] use worker_extension_cls for compatibility with V0 and V1 (#14185)

2025-03-07 00:32:46 +08:00

__init__.py

[MISC] Always import version library first in the vllm package (#12979)

2025-02-09 18:56:40 +08:00

_custom_ops.py

Update deprecated Python 3.8 typing (#13971)

2025-03-02 17:34:51 -08:00

_ipex_ops.py

Update deprecated Python 3.8 typing (#13971)

2025-03-02 17:34:51 -08:00

beam_search.py

Update deprecated Python 3.8 typing (#13971)

2025-03-02 17:34:51 -08:00

config.py

[RLHF] use worker_extension_cls for compatibility with V0 and V1 (#14185)

2025-03-07 00:32:46 +08:00

connections.py

Update deprecated Python 3.8 typing (#13971)

2025-03-02 17:34:51 -08:00

envs.py

[misc] Add FlashMLA as a new option of VLLM_ATTENTION_BACKEND env (#14267)

2025-03-05 21:28:50 +00:00

forward_context.py

[Bugfix] Remove num_tokens_across_dp (#14302)

2025-03-05 23:55:55 +00:00

logger.py

Update deprecated Python 3.8 typing (#13971)

2025-03-02 17:34:51 -08:00

logits_process.py

Update deprecated Python 3.8 typing (#13971)

2025-03-02 17:34:51 -08:00

outputs.py

Update deprecated Python 3.8 typing (#13971)

2025-03-02 17:34:51 -08:00

pooling_params.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

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

Reinstate best_of for V0 (#14356)

2025-03-06 08:34:22 -08:00

scalar_type.py

[NVIDIA] Support nvfp4 quantization (#12784)

2025-02-12 19:51:51 -08:00

scripts.py

[Frontend] Move CLI code into vllm.cmd package (#12971)

2025-02-12 23:12:21 -08:00

sequence.py

Update deprecated Python 3.8 typing (#13971)

2025-03-02 17:34:51 -08:00

test_utils.py

Use smaller embedding model when not testing model specifically (#13891)

2025-02-28 00:50:43 -08:00

tracing.py

Update deprecated Python 3.8 typing (#13971)

2025-03-02 17:34:51 -08:00

utils.py

[V1] EP/TP MoE + DP Attention (#13931)

2025-03-04 21:27:26 -08:00

version.py

[Metrics] Add --show-hidden-metrics-for-version CLI arg (#13295)

2025-02-22 00:20:45 -08:00