Kata Coder 5719a4e4e6 [Frontend] Support multimodal inputs for late-interaction scoring (ColQwen3) + NewModel: nvidia/nemotron-colembed (#34574) ...

Signed-off-by: craftsangjae <craftsangjae@gmail.com>

2026-02-20 20:01:40 -08:00

..

basic_correctness

[Feature] Support CPU Offloading without Pytorch Pinned Memory that leads to doubled allocation (#32993)

2026-02-13 08:11:26 -08:00

benchmarks

add --insecure arg to the vllm bench to skip TLS (#34026)

2026-02-10 22:23:52 +08:00

compile

[Bugfix] Fix quant RMS norm fusion for quantization with TMA-aligned scales (#33255)

2026-02-17 23:35:04 -08:00

config

[Bugfix] Exclude language_model_only key from MM AOT compile hash but include in model one (#34508)

2026-02-13 13:59:00 +00:00

cuda

[bugfix] [ROCm] Fix premature CUDA initialization in platform detection (#33941)

2026-02-06 16:17:55 -06:00

detokenizer

[CI/Build] Remove use of skip_v1 (#34699)

2026-02-18 12:19:11 +08:00

distributed

[AMD][CI] Fix test_custom_allreduce for A100 testgroup (#34735)

2026-02-20 21:33:04 +00:00

engine

Turn @config into a dataclass_transform (#31541)

2026-02-03 17:40:59 +00:00

entrypoints

[ROCm][CI] Loosen RemoteOpenAIServer Startup Timeout (#34922)

2026-02-20 05:37:49 +00:00

evals

[Bugfix] Fix NVFP4 TRTLLM MoE non-gated support; add gsm8k for Nemotron-3-Nano FP8+NVFP4 (#34725)

2026-02-18 09:39:22 -08:00

kernels

[Kernel] [Helion] [9/N] Canonicalize GPU variant names to base model names (#34928)

2026-02-20 19:55:51 -08:00

lora

[Bugfix] Fix lora tests (#34834)

2026-02-18 13:22:31 -08:00

model_executor

[CI/Build] Skip GCS test (#34057)

2026-02-07 08:52:38 -08:00

models

[Frontend] Support multimodal inputs for late-interaction scoring (ColQwen3) + NewModel: nvidia/nemotron-colembed (#34574)

2026-02-20 20:01:40 -08:00

multimodal

[Core] Fix SSRF bypass via backslash-@ URL parsing inconsistency (#34743)

2026-02-18 03:53:35 +00:00

plugins

[Misc] Update tests and examples for Prithvi/Terratorch models (#34416)

2026-02-13 23:03:51 -08:00

plugins_tests

(bugfix): Fixed encode in LLM entrypoint for IOProcessr plugin prompts (#34618)

2026-02-16 07:33:55 -08:00

prompts

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

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

quantization

[Bugfix] Add regression test for MoE quant_config under torch.compile (#34335)

2026-02-20 13:27:26 +08:00

reasoning

[Frontend] Fix reasoning_tokens for text-based parsers in Responses API (#33513)

2026-02-18 23:16:41 -08:00

renderers

[Bugfix] Fix edge case in UUID data parsing (#34884)

2026-02-19 02:24:30 -08:00

rocm/aiter

[Bugfix][Hardware][AMD] Fix exception types in AITER MLA FP8 check (#31177)

2026-01-06 14:10:59 +08:00

samplers

[CI/Build] Try to make beam search test less flaky (#34885)

2026-02-19 19:16:58 +08:00

standalone_tests

[CI][BugFix] ShellCheck cleanup to remove baseline and preserve runtime behavior (#34514)

2026-02-17 12:22:56 +00:00

system_messages

[V1] Implement Cascade Attention (#11635)

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

tokenizers_

[Refactor] Simplify BOS/EOS token handling (#34435)

2026-02-12 18:18:24 -08:00

tool_parsers

[Refactor] Simplify BOS/EOS token handling (#34435)

2026-02-12 18:18:24 -08:00

tool_use

[Refactor] [6/N] to simplify the vLLM openai chat_completion serving architecture (#32240)

2026-01-13 13:01:39 +00:00

tools

Turn @config into a dataclass_transform (#31541)

2026-02-03 17:40:59 +00:00

tracing

[CI][Tracing] Fix race condition by adding server readiness check (#34364)

2026-02-16 12:57:39 +00:00

transformers_utils

[UX] Use gguf repo_id:quant_type syntax for examples and docs (#33371)

2026-01-31 12:14:54 +08:00

utils_

[Refactor] Clean up pooling serial utils (#33665)

2026-02-03 10:29:18 +00:00

v1

[Kernel] Optimize sample_recovered_tokens_kernel (#34974)

2026-02-20 19:59:06 -08:00

vllm_test_utils

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

weight_loading

[Nightly CI] Remove CT Model (#33530)

2026-02-01 19:09:09 -08:00

__init__.py

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

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

ci_envs.py

[Model][0/N] Improve all pooling task | clean up (#25817)

2025-10-13 16:44:50 +08:00

conftest.py

[CI] Heavy refactoring of Voxtral multimodal audio model tests (#34294)

2026-02-13 20:04:29 -08:00

test_access_log_filter.py

[Logging] add --disable-access-log-for-endpoints CLI option (#30011)

2026-01-26 21:49:03 +00:00

test_attention_backend_registry.py

[1/N][Attention] Restructure attention: move files (#31916)

2026-01-09 13:10:24 -08:00

test_config.py

[CI][torch.compile] Reduce e2e fusion test time (#33293)

2026-02-04 19:09:03 -05:00

test_embedded_commit.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

test_envs.py

[Perf] Enable environment cache in EngineCore to enable the feature for UniProcExecutor as well (#29289)

2025-12-10 14:13:01 -05:00

test_inputs.py

[Refactor] Pass full VllmConfig to Renderer (#34485)

2026-02-12 22:48:38 -08:00

test_logger.py

[BugFix] respect VLLM_LOGGING_LEVEL in logger (#29761)

2025-12-02 07:49:16 +00:00

test_logprobs.py

[Core] Switch Flat logprob control from environment variable to SamplingParams (#28914)

2025-11-19 02:10:02 +00:00

test_outputs.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

test_pooling_params.py

[Refactor] Move task outside of PoolingParams.verify (#33796)

2026-02-05 09:33:11 +00:00

test_ray_env.py

[Ray] Propagate third-party env vars to Ray workers via prefix matching (#34383)

2026-02-17 01:08:42 -08:00

test_regression.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

test_scalartype.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

test_seed_behavior.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

test_sequence.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

test_triton_utils.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

test_version.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

test_vllm_port.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

utils.py

[ROCm][CI] Loosen RemoteOpenAIServer Startup Timeout (#34922)

2026-02-20 05:37:49 +00:00