Wushi Dong 0037b5746a

[Core] Eliminate redundant is_encoder_decoder lookups (20-40us/step) (#29800) ...

Signed-off-by: Wushi Dong <dongws@meta.com>

2025-12-02 07:08:07 +00:00

..

assets

…

attention

bugfix: correct attn output with base 2 or e (#28840)

2025-11-29 07:52:12 +08:00

benchmarks

[Chore] Move tokenizer initialization methods (#29793)

2025-12-02 13:33:37 +08:00

compilation

[Doc]: fixing typos in multiple files. (#29685)

2025-11-28 08:41:41 -08:00

config

[Misc] Throw error on unintended access to scheduler_config.max_model_len (#29771)

2025-12-02 10:58:44 +08:00

device_allocator

…

distributed

[Bugfix] Missing cached item in the MultiModalReceiverCache (#28525)

2025-12-01 10:18:07 -08:00

engine

[Core] Support reseting all running requests' KV while calling reset_prefix_cache (#28827)

2025-12-02 02:25:05 +00:00

entrypoints

[Core] Support reseting all running requests' KV while calling reset_prefix_cache (#28827)

2025-12-02 02:25:05 +00:00

inputs

[Chore] Enable passing tokenizer=None into MM processor (#29724)

2025-11-29 06:25:10 -08:00

logging_utils

[Misc] Colorize logs (#29017)

2025-11-19 19:26:04 -05:00

lora

[LoRA] Support FusedMoE LoRA Triton kernel for mxfp4 (#29708)

2025-11-30 10:37:25 +08:00

model_executor

Fix some Transformers nightly tests (#29802)

2025-12-02 07:05:27 +00:00

multimodal

[Chore] Move tokenizer initialization methods (#29793)

2025-12-02 13:33:37 +08:00

platforms

[CPU] Update torch 2.9.1 for CPU backend (#29664)

2025-11-28 13:37:54 +00:00

plugins

[Frontend] Resettle pooling entrypoints (#29634)

2025-12-01 15:30:43 +08:00

profiler

Make PyTorch profiler gzip and CUDA time dump configurable (#29568)

2025-12-01 04:30:46 +00:00

ray

[Small] Capture AttributeError when checking ray dependency. (#29024)

2025-11-20 22:54:10 -08:00

reasoning

[Misc] Refactor tokenizer interface (#29693)

2025-11-29 04:02:21 -08:00

third_party

…

tokenizers

[Chore] Move tokenizer initialization methods (#29793)

2025-12-02 13:33:37 +08:00

transformers_utils

[Chore] Move tokenizer initialization methods (#29793)

2025-12-02 13:33:37 +08:00

triton_utils

[mypy] Enable type checking for more directories (#29674)

2025-11-28 08:39:27 -08:00

usage

…

utils

[Misc] Remove redundant ClassRegistry (#29681)

2025-11-28 15:24:47 -08:00

v1

[Core] Eliminate redundant is_encoder_decoder lookups (20-40us/step) (#29800)

2025-12-02 07:08:07 +00:00

vllm_flash_attn

…

__init__.py

…

_aiter_ops.py

[ROCm][MLA] enable fp8 MLA decode on ROCm (#28032)

2025-11-25 10:15:02 +08:00

_bc_linter.py

…

_custom_ops.py

[Kernel][Quantization] add w4a8 support for marlin kernel (#24722)

2025-11-29 07:19:33 -08:00

_ipex_ops.py

…

beam_search.py

…

collect_env.py

…

connections.py

…

env_override.py

…

envs.py

[CI] Renovation of nightly wheel build & generation (take 2) (#29838)

2025-12-01 22:17:10 -08:00

forward_context.py

[Attention] Update attention imports (#29540)

2025-11-27 11:19:09 -05:00

logger.py

[Misc] Suppress log outputs when constructing the default vllm config. (#29291)

2025-11-25 03:00:44 -08:00

logits_process.py

[Misc] Refactor tokenizer interface (#29693)

2025-11-29 04:02:21 -08:00

logprobs.py

…

outputs.py

…

pooling_params.py

add add_truncate_prompt_tokens in repr for PoolingParams (#29683)

2025-11-28 08:41:05 -08:00

py.typed

…

sampling_params.py

[Misc] Refactor tokenizer interface (#29693)

2025-11-29 04:02:21 -08:00

scalar_type.py

…

scripts.py

…

sequence.py

…

tasks.py

…

tracing.py

…

version.py

…