Roger Wang 749be00a98 [Core][Multimodal] Allow passing multi_modal_uuids as multimodal identifiers. (#23394) ...

Signed-off-by: Roger Wang <hey@rogerw.io>

2025-08-30 18:01:22 -07:00

..

async_engine

…

basic_correctness

[test][RL] Add sleep level 2 test and fix reload with sleep mode (#23521)

2025-08-26 00:25:52 +08:00

benchmarks

Feature/benchmark/random mm data/images (#23119)

2025-08-25 01:28:35 -07:00

compile

[NVIDIA] Support SiluMul + NVFP4 quant fusion (#23671)

2025-08-28 19:36:50 +00:00

config

…

core

…

cuda

…

detokenizer

…

distributed

Update PyTorch to 2.8.0 (#20358)

2025-08-29 18:57:35 +08:00

encoder_decoder

…

engine

…

entrypoints

[Bugfix] Fix test_lora_resolvers.py (#23984)

2025-08-30 11:16:11 +00:00

evals/gsm8k

…

fastsafetensors_loader

…

kernels

[NVIDIA] Support SiluMul + NVFP4 quant fusion (#23671)

2025-08-28 19:36:50 +00:00

kv_transfer

…

lora

Update PyTorch to 2.8.0 (#20358)

2025-08-29 18:57:35 +08:00

metrics

…

mistral_tool_use

…

model_executor

…

models

[CI] Move testing image from remote URL to S3 (#23980)

2025-08-29 21:41:25 -07:00

mq_llm_engine

…

multimodal

[Core] Use key-only cache for BaseMultiModalProcessor (#23018)

2025-08-27 14:19:13 +08:00

neuron

…

plugins

…

plugins_tests

…

prompts

…

quantization

[Transform] [Quantization] Add transforms to compressed tensors (#22486)

2025-08-28 02:43:48 -04:00

reasoning

…

runai_model_streamer_test

…

samplers

[V0 Deprecation] Remove V0 Samplers test (#23862)

2025-08-28 18:05:52 -07:00

speculative_decoding/speculators

…

standalone_tests

…

system_messages

…

tensorizer_loader

…

tokenization

[Multimodal] Consolidate mm inputs into MultiModalFeatureSpec (#23779)

2025-08-29 18:36:57 +08:00

tool_use

[Bugfix]: Qwen3 Coder Tool Parser (#23099)

2025-08-26 19:58:32 -07:00

tools

…

tpu

…

tracing

…

utils_

Adds json_count_leaves utility function (#23899)

2025-08-29 05:28:13 -07:00

v1

[Core][Multimodal] Allow passing multi_modal_uuids as multimodal identifiers. (#23394)

2025-08-30 18:01:22 -07:00

vllm_test_utils

…

weight_loading

[Kernel/Quant] Remove the original marlin format and qqq (#23204)

2025-08-20 15:13:36 -04:00

worker

[V0 Deprecation] Remove pooling model support in V0 (#23434)

2025-08-29 00:04:02 -07:00

__init__.py

…

build_cython.py

…

conftest.py

[New Model]: Support GteNewModelForSequenceClassification (#23524)

2025-08-28 15:36:42 +08:00

test_cache_block_hashing.py

…

test_config.py

…

test_embedded_commit.py

…

test_inputs.py

…

test_logger.py

…

test_outputs.py

…

test_pooling_params.py

…

test_regression.py

…

test_routing_simulator.py

…

test_sampling_params.py

…

test_scalartype.py

…

test_seed_behavior.py

…

test_sequence.py

…

test_sharded_state_loader.py

…

test_test.py

…

test_triton_utils.py

…

test_version.py

…

test_vllm_port.py

…

utils.py

[CI Fix] Pin deepep and pplx tags in tools/ep_kernels/, gate multigpu tests (#23568)

2025-08-25 18:29:00 -07:00