This website requires JavaScript.
Explore
Help
Sign In
mirrors
/
vllm
Watch
0
Star
0
Fork
0
mirror of
https://github.com/vllm-project/vllm.git
synced
2026-10-28 09:45:26 +08:00
Code
Activity
Files
ae43d045c4e8e76bddf41fb39bc9dcc381dc260d
vllm
/
docs
/
serving
T
History
Martin Hickey
817fa3518c
[Frontend] Add derender output mode to generate (
#60082
)
...
Signed-off-by: Martin Hickey <
martin.hickey@ie.ibm.com
>
2026-10-21 08:20:46 -07:00
..
integrations
[Doc] Add Codex usage example (
#41358
)
2026-05-01 22:27:43 -07:00
online_serving
[Frontend] Add derender output mode to generate (
#60082
)
2026-10-21 08:20:46 -07:00
context_parallel_deployment.md
[Feature][Frontend] Expose effective attention block size for DCP (
#56538
)
2026-09-16 08:29:43 +00:00
data_parallel_deployment.md
[Bugfix] Fix external LB DP rank handling when replicas share nodes (
#53743
)
2026-09-21 17:19:14 +02:00
distributed_troubleshooting.md
[Examples] Resettle Disaggregated examples. (
#40759
)
2026-05-06 01:20:38 -07:00
expert_parallel_deployment.md
[feat] FlashInfer CuteDSL MegaMoE integration (
#54049
)
2026-10-02 15:43:33 -04:00
offline_inference.md
[Core][Frontend] Add weight version tagging for RL rollouts (
#49040
)
2026-07-28 14:35:29 +08:00
parallelism_scaling.md
[Core] Remove the legacy Ray compiled-graph executor (
#61712
)
2026-10-14 18:13:27 -07:00