Cyrus Leung 6879cd80ae

[Refactor] Pass tokenizer explicitly instead of binding to prompt update (#23542) ...

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

2025-08-25 06:31:57 -07:00

..

async_engine

[V0 Deprecation] Remove multi-step scheduling (#22138)

2025-08-12 20:18:39 -07:00

basic_correctness

[V0 Deprecation] Remove V0 FlashInfer attention backend (#22776)

2025-08-18 19:54:16 -07:00

benchmarks

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

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

compile

[NVIDIA][torch.compile] Support Flashinfer TRTLLM FP8-q/kv NVFP4-out Attention Kernel (#22703)

2025-08-22 22:09:05 +00:00

config

[V0 Deprecation] Remove multi-step scheduling (#22138)

2025-08-12 20:18:39 -07:00

core

[V0 Deprecation] Remove V0 FlashInfer attention backend (#22776)

2025-08-18 19:54:16 -07:00

cuda

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

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

detokenizer

[V1] support min_tokens for detokener (#22014)

2025-08-16 02:28:10 +00:00

distributed

[PERF] PyTorch Symmetric Memory All-Reduce (#20759)

2025-08-22 15:39:08 -06:00

encoder_decoder

[Misc] Add SPDX-FileCopyrightText (#19100)

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

engine

[V0 Deprecation] Remove multi-step scheduling (#22138)

2025-08-12 20:18:39 -07:00

entrypoints

(Misc): add missing test for zero truncation size. (#23457)

2025-08-24 18:12:47 +08:00

evals/gsm8k

[CI/Build] Replace lm-eval gsm8k tests with faster implementation (#23002)

2025-08-19 15:07:30 -07:00

fastsafetensors_loader

[Core] Support model loader plugins (#21067)

2025-07-24 01:49:44 -07:00

kernels

[kernel] Support W4A8 on Hopper (#23198)

2025-08-24 06:18:04 +00:00

kv_transfer

[V0 deprecation][P/D] Deprecate v0 KVConnectorBase code (1/2) (#21785)

2025-08-04 19:11:33 -07:00

lora

[V0 Deprecation] Remove V0 LoRA test (#23418)

2025-08-22 09:56:51 +00:00

metrics

[V0 Deprecation] Remove multi-step scheduling (#22138)

2025-08-12 20:18:39 -07:00

mistral_tool_use

[Misc] Add SPDX-FileCopyrightText (#19100)

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

model_executor

[V0 deprecation] Guided decoding (#21347)

2025-07-29 03:15:30 -07:00

models

[Bugfix] Fix Dense module loading for sentence-transformers embedding models (simplified V2) (#23408)

2025-08-25 05:39:24 +00:00

mq_llm_engine

[Flaky CI] Increase timeout tolerance for test_mp_crash_detection+test_default_mm_lora_chat_completions (#23028)

2025-08-16 18:33:08 +00:00

multimodal

[Refactor] Pass tokenizer explicitly instead of binding to prompt update (#23542)

2025-08-25 06:31:57 -07:00

neuron

[Misc] Remove deprecated args in v0.10 (#21349)

2025-07-22 05:26:39 -07:00

plugins

[gpt-oss] Enable gpt-oss on ampere (#22714)

2025-08-12 03:21:44 -07:00

plugins_tests

[Bugfix] Remove faulty test for oot attention backend (#22286)

2025-08-06 00:05:40 +00:00

prompts

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

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

quantization

[Deprecation] Remove prompt_token_ids arg fallback in LLM.generate and LLM.embed (#18800)

2025-08-22 10:56:57 +08:00

reasoning

Add think chunk (#21333)

2025-07-23 21:51:32 -07:00

runai_model_streamer_test

[Core] Support model loader plugins (#21067)

2025-07-24 01:49:44 -07:00

samplers

[V0 Deprecation] Remove multi-step scheduling (#22138)

2025-08-12 20:18:39 -07:00

speculative_decoding/speculators

Add: SupportsEagle3 interface for explicit EAGLE3 support (#22642)

2025-08-12 09:24:52 -07:00

standalone_tests

[CI] Remove duplicated docs build from buildkite (#22924)

2025-08-15 05:58:06 -07:00

system_messages

[V1] Implement Cascade Attention (#11635)

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

tensorizer_loader

[CI/Build] Fix tensorizer test for load_format change (#22583)

2025-08-10 19:30:00 -07:00

tokenization

[Misc] Modify the organization of GLM series (#22171)

2025-08-03 23:51:20 -07:00

tool_use

[New Model] Add Seed-Oss model (#23241)

2025-08-22 04:58:10 +00:00

tools

[Perf] Validate @config in pre-commit instead of dynamically (#20200)

2025-07-01 05:10:28 -04:00

tpu

[V0 Deprecation] Remove multi-step scheduling (#22138)

2025-08-12 20:18:39 -07:00

tracing

[Misc] Add SPDX-FileCopyrightText (#19100)

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

utils_

[V0 Deprecation] Remove args for multi-step scheduling (#22779)

2025-08-12 20:38:18 -07:00

v1

[Attention] Unify mamba and attention backend selection (#23171)

2025-08-25 09:09:36 +00:00

vllm_test_utils

[Misc] Add SPDX-FileCopyrightText (#19100)

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

weight_loading

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

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

worker

[V0 Deprecation] Remove multi-step scheduling (#22138)

2025-08-12 20:18:39 -07:00

__init__.py

…

build_cython.py

[Refactor] Refactor import utils (#20269)

2025-07-01 18:05:42 -07:00

conftest.py

[Model] Add multi_label_classification support (#23173)

2025-08-19 12:54:30 +00:00

test_cache_block_hashing.py

[Misc] Add SPDX-FileCopyrightText (#19100)

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

test_config.py

[Model] Pooling models default to using chunked prefill & prefix caching if supported. (#20930)

2025-08-11 09:41:37 -07:00

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

feat: Add --enable-log-outputs flag for logging model generations (#20707)

2025-08-06 23:10:13 -07:00

test_outputs.py

[Misc] Add SPDX-FileCopyrightText (#19100)

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

test_pooling_params.py

[Model] Pooling model activation supports per request control by PoolingParams (#20538)

2025-08-05 00:37:00 -07:00

test_regression.py

[Misc] Add SPDX-FileCopyrightText (#19100)

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

test_routing_simulator.py

[Misc] Support routing logic simulation (#21990)

2025-08-06 23:06:20 -07:00

test_sampling_params.py

[V0 deprecation] Guided decoding (#21347)

2025-07-29 03:15:30 -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

[Bugfix] fix IntermediateTensors equal method (#23027)

2025-08-18 02:58:11 -07:00

test_sharded_state_loader.py

[Misc] normalize multiprocessing Queue usage (#22371)

2025-08-08 01:57:27 +00:00

test_test.py

[Model] Gemma3n MM (#20495)

2025-08-09 09:56:25 -07:00

test_triton_utils.py

[Misc] Add SPDX-FileCopyrightText (#19100)

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

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

[Fix] correct tool_id for kimi-k2 when use tool_choice=required (#21259)

2025-08-20 12:59:54 -07:00