vllm/tests at lwilkinson/kv-layout/bind-kv-cache - vllm - Gitea: Git with a cup of tea

obscura/vllm

mirror of https://github.com/vllm-project/vllm.git synced 2026-06-06 00:16:14 +00:00

Files

T

History

Lucas Wilkinson 0f0ef3417b [KVConnector] Update connector tests for single packed K/V region

With K/V packed into a single contiguous region per block, the NIXL and
Mooncake transfer paths register one region per layer and coalesce block
transfers instead of emitting separate K/V halves. Update the unit tests
to match: detect the 4D blocks-first layout, expect one entry per tensor,
and expect coalesced (non-split) block transfers.

Co-authored-by: Claude

Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>

2026-06-03 23:59:24 -04:00

..

basic_correctness

[Test] Refactor hard coded device string in test files under compile/quantization/models/model_executor folders (#38901 )

2026-04-15 11:02:35 +08:00

[Benchmark] Enable reasoning-model (thinking) benchmarking via --chat-template-kwargs for client-rendered datasets (#44244 )

2026-06-02 22:49:51 -07:00

[ROCm][CI] Skip unbacked dynamic shapes tests on PyTorch < 2.11 (#44256 )

2026-06-01 19:09:01 -05:00

[Perf] FP8 FlashInfer Attn for ViT (#38065 )

2026-04-27 13:44:15 +08:00

[Hardware] Replace torch.cuda.device_count/current_device/set_device API (#36145 )

2026-03-12 07:57:47 -07:00

…

[EPLB] Nixl communicator optimization. Zero-copy transfers (#41633 )

2026-06-04 03:40:34 +00:00

[BugFix] HFValidationError with cloud storage URIs when HF_HUB_OFFLINE=1 (#39155 )

2026-05-27 10:53:32 -05:00

[Bugfix] Fix VLLMNotFoundError when using LoRA adapter name in poolin… (#44410 )

2026-06-04 02:22:03 +00:00

[CI] Add DSV4-Flash to gsm8k moe-refactor/config-b200.txt (#42111 )

2026-05-19 20:21:01 -07:00

[Perf] Set IR Op Priority Once at Worker Init (#42631 )

2026-05-15 15:56:13 +00:00

[Attention] Pack K/V into the content dim across attention backends

2026-06-03 23:59:24 -04:00

[Bugfix] Vendor MiniCPMV/MiniCPMO processors to unblock Transformers v5 (#44282 )

2026-06-02 07:14:38 -07:00

[ROCm][CI] Skip fp8 reload tests on gfx90a (MI250) (#44369 )

2026-06-02 22:27:14 -05:00

[MM][Perf][CG] Support ViT full CUDA graph for InternVL (#41759 )

2026-06-04 10:24:25 +08:00

[Multimodal] Automatically select registered video loader for VLM (#44126 )

2026-06-02 09:09:47 +00:00

[Bugfix] Honor tool_choice="none" in Chat Completions streaming (#42752 )

2026-06-03 13:27:45 -07:00

[Misc] Reorganize inputs (#35182 )

2026-03-25 10:22:54 -07:00

[CI/Build] Skip Prithvi/Terratorch model-registry tests when terratorch is missing (#41389 )

2026-04-30 12:47:55 -07:00

…

[Kernel][MoE] Add GELU_TANH to CPU, CUTLASS, and WNA16 MoE backends (#42027 )

2026-06-02 17:12:08 -04:00

[Bugfix] KimiK2ReasoningParser: guard against buffered end-token in streaming (#41068 )

2026-05-04 17:42:05 +00:00

[Frontend][Responses API] Move developer-to-system conversion into HF renderer (#43590 )

2026-06-03 14:52:24 +00:00

[ROCm][CI] Cleaning and restructuring amd-ci legacy pipeline (#34839 )

2026-03-19 14:30:58 -05:00

[Frontend] Add Support for MM Encoder/Decoder Beam Search (Offline) (#36153 )

2026-03-06 01:16:56 -08:00

[Feature] Support custom callable proposer backend for speculative decoding (#39487 )

2026-05-13 16:53:01 +00:00

standalone_tests

Add structure to requirements/ directory (#39024 )

2026-04-10 13:46:41 -07:00

system_messages

…

[CI] De-flake renderers/test_hf.py::test_resolve_content_format_fallbacks[Qwen/Qwen-VL-string] (#43064 )

2026-05-22 12:15:22 +08:00

[CI] Stabilize OpenAI schema fuzzing for malformed structural tags (#44131 )

2026-06-01 19:56:15 -07:00

[Misc] Use VLLMValidationError consistently in chat completion and completion protocol validators (#36254 )

2026-06-01 04:04:11 +00:00

build: embed image provenance metadata in vLLM containers (#40653 )

2026-04-29 03:07:41 -07:00

…

transformers_utils

[Bugfix] Fix _CONFIG_REGISTRY types getting wrong config class when on-disk model_type differs (#39554 )

2026-04-20 19:04:48 -07:00

[BugFix][CI] Fix added _has_module tests (#44248 )

2026-06-01 14:23:12 -07:00

[KVConnector] Update connector tests for single packed K/V region

2026-06-03 23:59:24 -04:00

vllm_test_utils

…

[Quant] Consolidate GPTQ: rename gptq_marlin.py to auto_gptq.py (#38288 )

2026-05-15 08:25:52 +08:00

__init__.py

…

ci_envs.py

…

conftest.py

[ROCm][CI] Stabilize runner teardown between sampler tests (#43023 )

2026-05-23 12:19:54 +08:00

test_access_log_filter.py

…

test_attention_backend_registry.py

…

test_config.py

[MRV2] Also enable MRV2 for Llama and Mistral dense models (#43458 )

2026-06-02 11:18:46 -07:00

test_embedded_commit.py

…

test_envs.py

[Frontend][RFC] Rust front-end integration (#40848 )

2026-05-21 12:24:48 +08:00

test_fxgraphcache_pickle_patch.py

[ZenCPU] Make PT Backport Patch Accessible to vLLM (#38205 )

2026-04-10 08:29:35 +00:00

test_inputs.py

…

test_jit_monitor.py

[Feature] Add Triton kernel JIT compilation monitor for inference (#40137 )

2026-05-05 14:08:57 +04:00

test_logger.py

…

test_logprobs.py

…

test_outputs.py

…

test_pooling_params.py

[Model] Deprecate the score task (this will not affect users). (#37537 )

2026-03-20 08:07:56 +00:00

test_ray_env_utils.py

[Feat][Executor] Introduce RayExecutorV2 (#36836 )

2026-04-01 14:34:29 -07:00

test_ray_env.py

fix nixl side-channel host selection (#41806 )

2026-05-11 07:40:37 +00:00

test_regression.py

[CI/Build] Use modelscope's international site for regression test (#42176 )

2026-05-09 19:47:09 -07:00

test_scalartype.py

…

test_seed_behavior.py

…

test_sequence.py

…

test_triton_utils.py

…

test_version.py

…

test_vllm_port.py

…

test_zen_cpu_platform_detection.py

In-Tree AMD Zen CPU Backend via zentorch [1/N] (#35970 )

2026-03-15 23:35:35 +00:00

utils.py

[ROCm][CI] Extend ROCm quick reduce coverage (#40990 )

2026-05-26 21:57:13 +08:00