Alex Kogan 27949354fa

[Feature] A calibration-free RTN-based quantization for accurate and accelerated INT4/INT8 inference (#18768) ...

Signed-off-by: Alex Kogan <alex.kogan@oracle.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>

2025-07-01 05:44:38 +00:00

..

async_engine

[Frontend] Make TIMEOUT_KEEP_ALIVE configurable through env var (#18472)

2025-06-09 21:41:21 +00:00

basic_correctness

Fixing Chunked Prefill Test. (#19762)

2025-06-19 01:36:16 -07:00

benchmarks

[Spec Decode][Benchmark] Generalize spec decode offline benchmark to more methods and datasets (#18847)

2025-06-12 10:30:56 -07:00

compile

use .dev for version comparison with pytorch nightly release (#20031)

2025-06-24 21:52:16 +00:00

config

[Bugfix] Allow CUDA_VISIBLE_DEVICES='' in Platform.device_id_to_physical_device_id (#18979)

2025-06-26 00:01:57 -07:00

core

[Bugfix][Core] Prefix caching causes incorrect outputs due to outdated ComputedBlocksTracker (#18957)

2025-06-15 21:56:37 -07:00

cuda

[Bugfix][Ray] Set the cuda context eagerly in the ray worker (#19583)

2025-06-19 22:01:16 -07:00

detokenizer

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

distributed

[Feature] add quick all reduce (#19744)

2025-06-26 20:54:24 -07:00

encoder_decoder

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

engine

[CLI] Improve CLI arg parsing for -O/--compilation-config (#20156)

2025-07-01 01:03:13 +00:00

entrypoints

[Bugfix] Fix include prompt in stream response when echo=true (#15233)

2025-07-01 01:30:14 +00:00

fastsafetensors_loader

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

kernels

[Unit Test] Add unit test for deep gemm (#20090)

2025-06-30 10:26:42 -06:00

kv_transfer

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

lora

[CI] change spell checker from codespell to typos (#18711)

2025-06-11 19:57:10 -07:00

metrics

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

mistral_tool_use

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

model_executor

[Fix][torch.compile] Enable custom ops by default when Inductor off (#20102)

2025-06-27 09:00:42 -06:00

models

[Model] support dots1 (#18254)

2025-06-29 19:34:36 -07:00

mq_llm_engine

[Misc] Add type assertion of request_id for LLMEngine.add_request (#19700)

2025-06-27 22:47:36 -07:00

multi_step

Adding "AMD: Multi-step Tests" to amdproduction. (#19508)

2025-06-13 17:08:51 -07:00

multimodal

[Core] [Bugfix] [Multimodal] Fix multimodal profiling and generation for SFT/PTQed models (#20058)

2025-06-30 17:26:49 +00:00

neuron

[Refactor] Remove duplicate ceil_div (#20023)

2025-06-25 05:19:09 +00:00

plugins

[custom_op][vllm-plugin] update custom_op class to use op_registry (#19164)

2025-06-20 07:44:56 -07:00

plugins_tests

[custom_op][vllm-plugin] update custom_op class to use op_registry (#19164)

2025-06-20 07:44:56 -07:00

prefix_caching

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

prompt_adapter

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

prompts

[BugFix] Fix input positions for long context with sliding window (#2088)

2023-12-13 12:28:13 -08:00

quantization

[Feature] A calibration-free RTN-based quantization for accurate and accelerated INT4/INT8 inference (#18768)

2025-07-01 05:44:38 +00:00

reasoning

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

runai_model_streamer_test

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

samplers

[CI] change spell checker from codespell to typos (#18711)

2025-06-11 19:57:10 -07:00

spec_decode

[CI Fix] Try fixing eagle e2e test OOM by reducing block allocation (#20213)

2025-06-29 10:31:37 +08:00

standalone_tests

[CI] Sync test dependency with test.in for torch nightly (#19632)

2025-06-26 20:55:25 -07:00

system_messages

[V1] Implement Cascade Attention (#11635)

2025-01-01 21:56:46 +09:00

tensorizer_loader

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

tokenization

Support embedding models in V1 (#16188)

2025-06-18 21:36:33 -07:00

tool_use

Add xLAM tool parser support (#17148)

2025-06-19 14:26:41 +08:00

tpu

[TPU] update torch_xla pin (#19231)

2025-06-06 04:27:38 +00:00

tracing

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

v1

[Optimization] Use Shared CachedRequestData Instance Across All Requests (#20232)

2025-06-30 09:07:50 -07:00

vllm_test_utils

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

weight_loading

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

worker

[CI] change spell checker from codespell to typos (#18711)

2025-06-11 19:57:10 -07:00

__init__.py

[Small] Formatter only checks lints in changed files (#1528)

2023-10-31 15:39:38 -07:00

build_cython.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

conftest.py

[Bugfix][v1] Fix step pooler implementation and step pooling usage in v1 (#19956)

2025-06-23 18:38:06 +00:00

test_cache_block_hashing.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

test_config.py

[Misc] Fix skipped max-model-len validation when deriving max model length from tokenizer config (#19660)

2025-06-16 06:30:29 +00:00

test_embedded_commit.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

test_inputs.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

test_logger.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

test_outputs.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

test_regression.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

test_sampling_params.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

test_scalartype.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

test_seed_behavior.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

test_sequence.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

test_sharded_state_loader.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

test_triton_utils.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

test_utils.py

[CLI] Improve CLI arg parsing for -O/--compilation-config (#20156)

2025-07-01 01:03:13 +00:00

test_version.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

test_vllm_port.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

utils.py

[CUDA] Enable full cudagraph for FlashMLA (#18581)

2025-06-13 18:12:26 +00:00