Nick HillandZhuohan Li 80e00e5ac6 [Core] Pick extensible KV cache memory from #47363 ...

Reserve the KV cache address range with CUDA virtual memory, commit a
minimal prefix before CUDA graph capture, measure real post-capture
memory usage, then commit the final KV cache size with stable tensor
addresses. Opt-in via --enable-extensible-kv-cache.

Squashed pick of vllm-project/vllm#47363.

Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>
Signed-off-by: Nick Hill <nickhill@us.ibm.com>

2026-07-20 14:42:55 +01:00

..

__init__.py

[Misc] Move tensor schema tests (#22612)

2025-08-11 00:15:27 -07:00

test_argparse_utils.py

[UX] Enable nested configs in config yaml files (#33193)

2026-01-28 16:54:25 -05:00

test_async_utils.py

[Bugfix][Core] Close underlying iterator in merge_async_iterators single-iterator fast path (#44726)

2026-07-07 05:13:41 -07:00

test_cache.py

[Misc] Move LRUCache into its own file (#26342)

2025-10-07 15:08:40 +00:00

test_collection_utils.py

[Model] Extend collect_children and no_init_weights contexts (#32757)

2026-01-22 08:20:27 +00:00

test_extensible_tensor.py

[Core] Pick extensible KV cache memory from #47363

2026-07-20 14:42:55 +01:00

test_func_utils.py

[Refactor] Remove unused utils (#38153)

2026-03-26 17:08:19 +08:00

test_gc_utils.py

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

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

test_gpu_sync_debug.py

[Core] Add VLLM_GPU_SYNC_CHECK env var (#44800)

2026-06-26 08:24:33 -07:00

test_hashing.py

[Misc] Move utils to avoid conflicts with stdlib, and move tests (#27169)

2025-10-19 05:20:55 -07:00

test_import_utils.py

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

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

test_jsontree.py

[Chore] Separate out vllm.utils.func (#26904)

2025-10-15 13:03:58 +00:00

test_mem_utils.py

[Platform] Replace torch.cuda.mem_get_info with torch.accelerator.get_memory_info (#44825)

2026-06-30 14:39:52 +08:00

test_network_utils.py

[BugFix] avoid infinite loop with VLLM_PORT and get_open_ports_list (#36191)

2026-03-05 22:15:29 -08:00

test_numa_utils.py

[Bugfix][Core] Fall back when numactl --membind is blocked in constrained containers (#45438)

2026-06-16 09:49:56 -07:00

test_ray_utils.py

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

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

test_serial_utils.py

[Frontend] Add multimodal support to /inference/v1/generate endpoint (#38405)

2026-04-17 20:31:56 -07:00

test_spawn_decorator.py

[Bugfix] Fix spawn_new_process_for_each_test silently swallowing test failures (#41423)

2026-05-06 11:17:15 -04:00

test_system_utils.py

[Feature] NUMA binding support for GPU workers (#38635)

2026-04-08 09:55:24 -07:00

test_tensor_schema.py

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

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

test_torch_utils.py

use the same stream for cuda graph catpure and replay for NCCL (#29207)

2025-12-25 19:10:03 +08:00