xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-04-14 17:17:04 +08:00
Code Issues Packages Projects Releases Wiki Activity
vllm/vllm/v1
History
Corey Lowman 4ebc513fc1 Add VLLM_NVTX_SCOPES_FOR_PROFILING=1 to enable nvtx.annotate scopes (#25501) 
Signed-off-by: Corey Lowman <clowman1993@gmail.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:54 -07:00
..
attention
[V1][Kernel] Add triton implementation for reshape_and_cache_flash (#24503)
2025-10-03 13:35:54 -07:00
core
[Core] Use KVCacheBlock as much as possible instead of dict[block_id, KVCacheBlock] (#24830)
2025-10-03 13:35:54 -07:00
engine
[DP] support torchrun external launcher with Data Parallelism (#24899)
2025-10-03 13:35:53 -07:00
executor
[V0 Deprecation] Remove V0 MP executor (#25329)
2025-10-03 13:35:53 -07:00
kv_offload
[KV offload][5/N] Add CPUOffloadingSpec (#24251)
2025-10-03 13:35:53 -07:00
metrics
[P/D][Nixl] Introduce KVTransferMetrics and aggregation strategy (#22188)
2025-09-19 11:09:14 +00:00
pool
[Performance] V1 Pooling Models E2E Performance Optimization (#23162)
2025-08-21 13:26:09 +00:00
sample
[Docs] Fix warnings in mkdocs build (continued) (#25042)
2025-10-03 13:35:53 -07:00
spec_decode
[Speculators][Speculative Decoding] Fix gpt-oss eagle3 accuracy issue (#25406)
2025-10-03 13:35:54 -07:00
structured_output
[Build] Update Xgrammar to 0.1.25 (#25467)
2025-10-03 13:35:54 -07:00
worker
[BugFix] Fix OOM in vLLM replicas by ensuring consistent NCCL memory accounting (#25359)
2025-10-03 13:35:54 -07:00
__init__.py
[V1] AsyncLLM Implementation (#9826)
2024-11-11 23:05:38 +00:00
cudagraph_dispatcher.py
[torch.compile] CUDAGraph Inductor partition integration (#24281)
2025-10-03 13:35:53 -07:00
kv_cache_interface.py
[Hybrid Allocator] Support full attention with different hidden size (#25101)
2025-10-03 13:35:53 -07:00
outputs.py
[P/D][Nixl] Introduce KVTransferMetrics and aggregation strategy (#22188)
2025-09-19 11:09:14 +00:00
request.py
[CORE] Prompt Embeddings Support for v1 Engine (#24278)
2025-09-19 08:03:09 +08:00
serial_utils.py
[Misc] Support more collective_rpc return types (#25294)
2025-10-03 13:35:53 -07:00
utils.py
Add VLLM_NVTX_SCOPES_FOR_PROFILING=1 to enable nvtx.annotate scopes (#25501)
2025-10-03 13:35:54 -07:00