Woosuk Kwon 371d04d39b

[V1] Use FlashInfer Sampling Kernel for Top-P & Top-K Sampling (#11394) ...

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

2024-12-27 09:32:38 +09:00

..

async_engine

[MISC] Consolidate cleanup() and refactor offline_inference_with_prefix.py (#9510)

2024-10-18 14:30:55 -07:00

basic_correctness

[V1] Unify VLLM_ENABLE_V1_MULTIPROCESSING handling in RayExecutor (#11472)

2024-12-24 19:49:46 -08:00

compile

[torch.compile] Dynamic fp8 + rms_norm fusion (#10906)

2024-12-13 03:19:23 +00:00

core

[Core] support LoRA and prompt adapter in content-based hashing for Block Manager v2 prefix caching (#8240)

2024-12-13 07:51:25 -08:00

data

[Bugfix] Fix load config when using bools (#9533)

2024-10-27 13:46:41 -04:00

distributed

[Model] Refactor Ultravox to use merged input processor (#11198)

2024-12-16 10:09:53 +00:00

encoder_decoder

[Encoder Decoder] Update Mllama to run with both FlashAttention and XFormers (#9982)

2024-11-12 10:53:57 -08:00

engine

[torch.compile] allow candidate compile sizes (#10984)

2024-12-08 11:05:21 +00:00

entrypoints

[Frontend] Online Pooling API (#11457)

2024-12-24 17:54:30 +08:00

fp8_kv

Enable scaled FP8 (e4m3fn) KV cache on ROCm (AMD GPU) (#3290)

2024-04-03 14:15:55 -07:00

kernels

[Model] [Quantization] Support deepseek_v3 w8a8 fp8 block-wise quantization (#11523)

2024-12-26 15:33:30 -08:00

kv_transfer

[Misc] Update disaggregation benchmark scripts and test logs (#11456)

2024-12-25 06:58:48 +00:00

lora

[Misc][LoRA] Fix LoRA weight mapper (#11495)

2024-12-26 15:52:48 +08:00

metrics

monitor metrics of tokens per step using cudagraph batchsizes (#11031)

2024-12-09 22:35:36 -08:00

model_executor

[CI] Expand test_guided_generate to test all backends (#11313)

2024-12-19 04:00:38 +00:00

models

[Misc] Move some multimodal utils to modality-specific modules (#11494)

2024-12-26 04:23:20 +00:00

mq_llm_engine

[Bugfix][core] replace heartbeat with pid check (#9818)

2024-10-30 09:34:07 -07:00

multi_step

[Core] Deprecating block manager v1 and make block manager v2 default (#8704)

2024-10-17 11:38:15 -05:00

multimodal

[Misc] Move some multimodal utils to modality-specific modules (#11494)

2024-12-26 04:23:20 +00:00

plugins/vllm_add_dummy_model

[Misc] Move weights mapper (#11443)

2024-12-24 13:05:25 +00:00

prefix_caching

Prefix Cache Aware Scheduling [1/n] (#10128)

2024-11-22 21:15:55 -08:00

prompt_adapter

[CORE] Adding support for insertion of soft-tuned prompts (#4645)

2024-07-09 13:26:36 -07:00

prompts

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

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

quantization

[Misc] add w8a8 asym models (#11075)

2024-12-23 13:33:20 -05:00

runai_model_streamer

[Core] Loading model from S3 using RunAI Model Streamer as optional loader (#10192)

2024-12-20 16:46:24 +00:00

samplers

[Bugfix] Fix spec decoding when seed is none in a batch (#10863)

2024-12-20 05:15:31 +00:00

spec_decode

[Bugfix][SpecDecode] apply sampling parameters to target probabilities for consistency in rejection sampling. (#10198)

2024-11-27 05:07:30 +00:00

standalone_tests

[ci][build] add tests for python only compilation (#10915)

2024-12-05 08:54:47 -08:00

tensorizer_loader

[Misc] Add placeholder module (#11501)

2024-12-26 13:12:51 +00:00

tokenization

[CI/Build] drop support for Python 3.8 EOL (#8464)

2024-11-06 07:11:55 +00:00

tool_use

[Model] IBM Granite 3.1 (#11307)

2024-12-19 11:27:24 +08:00

tpu

[9/N] torch.compile LLM usage (#10552)

2024-11-21 19:13:31 -08:00

tracing

[BugFix] Prevent exporting duplicate OpenTelemetry spans (#9017)

2024-10-22 11:11:53 -07:00

v1

[V1] Use FlashInfer Sampling Kernel for Top-P & Top-K Sampling (#11394)

2024-12-27 09:32:38 +09:00

vllm_test_utils

[ci] fix slow tests (#10698)

2024-11-27 09:26:14 -08:00

weight_loading

[Kernel]: Cutlass 2:4 Sparsity + FP8/Int8 Quant Support (#10995)

2024-12-18 09:57:16 -05:00

worker

[core] overhaul memory profiling and fix backward compatibility (#10511)

2024-12-16 13:32:25 -08:00

__init__.py

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

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

conftest.py

[Frontend] Separate pooling APIs in offline inference (#11129)

2024-12-13 10:40:07 +00:00

test_cache_block_hashing.py

[Core] Make encoder-decoder inputs a nested structure to be more composable (#9604)

2024-11-05 10:07:31 +08:00

test_config.py

[Misc] Split up pooling tasks (#10820)

2024-12-11 01:28:00 -08:00

test_embedded_commit.py

[CI/Build] use setuptools-scm to set __version__ (#4738)

2024-09-23 09:44:26 -07:00

test_inputs.py

[Core][Frontend] Add Support for Inference Time mm_processor_kwargs (#9131)

2024-10-08 14:12:56 +00:00

test_logger.py

Rename vllm.logging to vllm.logging_utils (#10134)

2024-11-08 20:53:24 +00:00

test_logits_processor.py

[Core] Factor out common code in SequenceData and Sequence (#8675)

2024-09-21 02:30:39 +00:00

test_regression.py

Bugfix: fix broken of download models from modelscope (#5233)

2024-06-06 09:28:10 -07:00

test_sampling_params.py

[Bugfix] fix crash if max_tokens=None (#2570)

2024-01-23 22:38:55 -08:00

test_scalartype.py

[Bugfix] Fix support for dimension like integers and ScalarType (#9299)

2024-10-17 19:08:34 +00:00

test_sequence.py

[Core] Factor out common code in SequenceData and Sequence (#8675)

2024-09-21 02:30:39 +00:00

test_sharded_state_loader.py

[CI/Build] Replaced some models on tests for smaller ones (#9570)

2024-10-22 04:52:14 +00:00

test_utils.py

[Bugfix] Fix request cancellation without polling (#11190)

2024-12-17 12:26:32 -08:00

utils.py

[Bugfix] Fix request cancellation without polling (#11190)

2024-12-17 12:26:32 -08:00