vLLM/vllm at 1cf0719ebdcd67ecdd5801da9154e56683fa7360 - vLLM

adapter_commons

…

assets

[Model][VLM] Add Qwen2.5-Omni model support (thinker only) (#15130 )

2025-04-18 23:14:36 -07:00

attention

[Quantization][FP8] Add support for FP8 models with input_scale for output projection and QK quantization (#15734 )

2025-04-25 00:45:02 -07:00

benchmarks

Fix Python packaging edge cases (#17159 )

2025-04-26 06:15:07 +08:00

compilation

[Bugfix] [pytorch] Patch AOTAutogradCache._get_shape_env (#17142 )

2025-04-26 11:28:20 +08:00

core

…

device_allocator

…

distributed

[v1] [P/D] Adding LMCache KV connector for v1 (#16625 )

2025-04-26 03:03:38 +00:00

engine

[AMD][FP8][BugFix] Remove V1 check in arg_utils.py for FP8 since it is not necessary (#17215 )

2025-04-25 19:55:05 -07:00

entrypoints

[BugFix][Frontend] Fix LLM.chat() tokenization (#16081 )

2025-04-25 22:20:05 +00:00

executor

[Misc] Clean up redundant code in uniproc_executor.py (#16762 )

2025-04-24 22:49:30 -07:00

inputs

Simplify TokenizerGroup (#16790 )

2025-04-24 04:43:56 -07:00

logging_utils

…

lora

[Misc] Enable vLLM to Dynamically Load LoRA from a Remote Server (#10546 )

2025-04-15 22:31:38 +00:00

model_executor

[AMD][FP8][BugFix] Remove V1 check in arg_utils.py for FP8 since it is not necessary (#17215 )

2025-04-25 19:55:05 -07:00

multimodal

[Model] Refactor Phi-4-multimodal to use merged processor and support V1 (#15477 )

2025-04-19 02:26:11 -07:00

platforms

[BugFix] Revert ROCm Custom Paged Attention Env Flag Check (#17022 )

2025-04-22 19:17:48 -07:00

plugins

…

profiler

…

prompt_adapter

…

reasoning

[BugFix] fix some typos found by typos. (#16314 )

2025-04-09 03:43:59 -07:00

spec_decode

[Chore] Remove Sampler from Model Code (#17084 )

2025-04-24 02:49:33 -07:00

third_party

[BugFix] fix some typos found by typos. (#16314 )

2025-04-09 03:43:59 -07:00

transformers_utils

Use Transformers helper get_text_config() instead of checking for text_config (#17105 )

2025-04-25 08:47:35 -07:00

triton_utils

[Bugfix][Misc] Use TritonPlaceholderModule to defensively import triton (#15099 )

2025-04-24 22:51:02 -07:00

usage

[V1] Move usage stats to worker and start logging TPU hardware (#16211 )

2025-04-25 14:06:01 -06:00

v1

[Minor][Spec Decode] Add use_eagle to SpeculativeConfig (#17213 )

2025-04-25 21:08:15 -07:00

vllm_flash_attn

Fix Python packaging edge cases (#17159 )

2025-04-26 06:15:07 +08:00

worker

Use Transformers helper get_text_config() instead of checking for text_config (#17105 )

2025-04-25 08:47:35 -07:00

__init__.py

[misc] instruct pytorch to use nvml-based cuda check (#15951 )

2025-04-03 01:02:58 +08:00

_custom_ops.py

[Performance][ROCm] Add skinny gemms for unquantized linear on ROCm (#15830 )

2025-04-21 20:46:22 -07:00

_ipex_ops.py

…

beam_search.py

[Core][Bugfix] Fix Offline MM Beam Search (#16390 )

2025-04-15 10:33:02 +08:00

collect_env.py

[Misc] fix collect_env version parse (#15267 )

2025-04-21 20:29:40 +08:00

config.py

[Minor][Spec Decode] Add use_eagle to SpeculativeConfig (#17213 )

2025-04-25 21:08:15 -07:00

connections.py

…

env_override.py

[misc] tune some env vars for GB200 (#16992 )

2025-04-23 10:59:48 +08:00

envs.py

Addendum Fix to support FIPS enabled machines with MD5 hashing (#17043 )

2025-04-23 19:55:00 -07:00

forward_context.py

[P/D][V1] KV Connector API V1 (#15960 )

2025-04-17 13:22:40 -07:00

jsontree.py

…

logger.py

…

logits_process.py

…

outputs.py

[Bugfix][Core] add seq_id_to_seq_group clearing to avoid memory leak when s… (#16472 )

2025-04-24 11:25:37 +08:00

pooling_params.py

[Frontend] Using matryoshka_dimensions control the allowed output dimensions. (#16970 )

2025-04-24 07:06:28 -07:00

py.typed

…

sampling_params.py

[Bugfix] Fix the issue where llm.generate cannot be called repeatedly after setting GuidedDecodingParams (#16767 )

2025-04-22 06:02:20 +00:00

scalar_type.py

…

scripts.py

…

sequence.py

…

test_utils.py

…

tracing.py

…

utils.py

[Bugfix][Misc] Use TritonPlaceholderModule to defensively import triton (#15099 )

2025-04-24 22:51:02 -07:00

version.py

…