Andrew Sansom cc2a77d7f1

[Core] [Bugfix] Add Input Embeddings (#15428) ...

Signed-off-by: Andrew Sansom <andrew@protopia.ai>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: 临景 <linjing.yx@alibaba-inc.com>
Co-authored-by: Bryce1010 <bryceyx@gmail.com>
Co-authored-by: Nan2018 <nan@protopia.ai>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>

2025-05-02 01:06:39 -07:00

..

async_engine

[V1] V1 Enablement Oracle (#13726)

2025-03-14 22:02:20 -07:00

basic_correctness

[core] Add tags parameter to wake_up() (#15500)

2025-04-02 01:59:27 -07:00

benchmarks

Add vllm bench [latency, throughput] CLI commands (#16508)

2025-04-14 23:10:35 -07:00

compile

[torch.compile] Add torch inductor pass for fusing silu_and_mul with subsequent scaled_fp8_quant operations (#10867)

2025-05-01 07:59:28 -07:00

config

[Feature] specify model in config.yaml (#15798)

2025-04-01 01:20:06 -07:00

core

[Core] [Bugfix] Add Input Embeddings (#15428)

2025-05-02 01:06:39 -07:00

detokenizer

[V1] V1 Enablement Oracle (#13726)

2025-03-14 22:02:20 -07:00

distributed

[V1][Metrics] add support for kv event publishing (#16750)

2025-04-30 07:44:45 -07:00

encoder_decoder

[V1] V1 Enablement Oracle (#13726)

2025-03-14 22:02:20 -07:00

engine

Improve configs - ModelConfig (#17130)

2025-04-30 10:38:22 +08:00

entrypoints

[Feature][Frontend]: Deprecate --enable-reasoning (#17452)

2025-05-01 06:46:16 -07:00

fastsafetensors_loader

[Core] Integrate fastsafetensors loader for loading model weights (#10647)

2025-03-24 08:08:02 -07:00

kernels

[torch.compile] Add torch inductor pass for fusing silu_and_mul with subsequent scaled_fp8_quant operations (#10867)

2025-05-01 07:59:28 -07:00

kv_transfer

[CI] Actually run tests/kv_transfer/test_disagg.py in CI (#17555)

2025-05-02 04:05:04 +00:00

lora

[Bugfix] Fix Lora Name Parsing (#17196)

2025-04-27 20:33:09 +08:00

metrics

[V1][Spec Decode] Remove deprecated spec decode config params (#15466)

2025-03-31 09:19:35 -07:00

mistral_tool_use

…

model_executor

Simplify (and fix) passing of guided decoding backend options (#17008)

2025-04-29 19:02:23 +00:00

models

[Core] [Bugfix] Add Input Embeddings (#15428)

2025-05-02 01:06:39 -07:00

mq_llm_engine

[Misc] Replace os environ to monkeypatch in test suite (#14516)

2025-03-16 20:35:57 -07:00

multi_step

[Misc] Replace os environ to monkeypatch in test suite (#14516)

2025-03-16 20:35:57 -07:00

multimodal

[V1] Enable multi-input by default (#15799)

2025-04-12 08:52:39 +00:00

neuron

[Neuron][kernel] Fuse kv cache into a single tensor (#15911)

2025-04-03 09:51:32 -07:00

plugins

…

plugins_tests

[V1] Scheduler Refactoring [1/N] - Add Scheduler Interface (#15250)

2025-03-20 17:50:43 -07:00

prefix_caching

[Misc] Replace os environ to monkeypatch in test suite (#14516)

2025-03-16 20:35:57 -07:00

prompt_adapter

…

prompts

…

quantization

Add pt_load_map_location to allow loading to cuda (#16869)

2025-05-01 23:23:42 -07:00

reasoning

[Bugfix] add qwen3 reasoning-parser fix content is None when disable … (#17369)

2025-04-29 16:32:40 +00:00

runai_model_streamer_test

…

samplers

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

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

spec_decode

Fix more broken speculative decode tests (#17450)

2025-05-01 06:05:58 -07:00

standalone_tests

[Build] Make sure local main branch is synced when VLLM_USE_PRECOMPILED=1 (#13921)

2025-03-03 16:43:14 +08:00

system_messages

…

tensorizer_loader

[Core] Update dtype detection and defaults (#14858)

2025-03-19 13:49:33 +08:00

tokenization

[Core] Prevent side-channel attacks via cache salting (#17045)

2025-04-30 20:27:21 +08:00

tool_use

Add chat template for Llama 4 models (#16428)

2025-04-24 20:19:36 +00:00

tpu

[TPU][V1] Refine tpu_model_runner to mitigate future recompilation issues (#16275)

2025-04-09 18:51:51 -06:00

tracing

[Misc] Replace os environ to monkeypatch in test suite (#14516)

2025-03-16 20:35:57 -07:00

v1

[CI][Bugfix] Fix failing V1 Test due to missing 'cache_salt' arg (#17500)

2025-04-30 21:03:30 -07:00

vllm_test_utils

…

weight_loading

[V1] V1 Enablement Oracle (#13726)

2025-03-14 22:02:20 -07:00

worker

[Core] [Bugfix] Add Input Embeddings (#15428)

2025-05-02 01:06:39 -07:00

__init__.py

…

build_cython.py

[Build] Cython compilation support fix (#14296)

2025-03-24 23:37:54 +00:00

conftest.py

[Core] [Bugfix] Add Input Embeddings (#15428)

2025-05-02 01:06:39 -07:00

test_cache_block_hashing.py

…

test_config.py

Add pt_load_map_location to allow loading to cuda (#16869)

2025-05-01 23:23:42 -07:00

test_embedded_commit.py

…

test_inputs.py

…

test_logger.py

…

test_logits_processor.py

…

test_regression.py

[Misc] Replace os environ to monkeypatch in test suite (#14516)

2025-03-16 20:35:57 -07:00

test_sampling_params.py

[Bugfix][Frontend] respect provided default guided decoding backend (#15476)

2025-04-09 05:11:10 -07:00

test_scalartype.py

…

test_seed_behavior.py

…

test_sequence.py

…

test_sharded_state_loader.py

[Misc] Fix test_sharded_state_loader.py(#16004) (#16005)

2025-04-09 14:47:30 +08:00

test_utils.py

[Core] Enable IPv6 with vllm.utils.make_zmq_socket() (#16506)

2025-05-01 09:38:18 +00:00

test_version.py

…

utils.py

[Metrics] Hide deprecated metrics (#15458)

2025-04-02 07:37:19 -07:00