-
-
Notifications
You must be signed in to change notification settings - Fork 5.8k
Pull requests: vllm-project/vllm
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Remove unused kwargs from model definitions
documentation
Improvements or additions to documentation
ready
ONLY add when PR is ready to merge/full CI is needed
speculative-decoding
v1
#13555
opened Feb 19, 2025 by
hmellor
Loading…
fix(chunked prefill): don't schedule prefill if freeing kv cache
#13539
opened Feb 19, 2025 by
toslunar
Loading…
[Misc] add mm_processor_kwargs to extra_body for Qwen2.5-VL
frontend
#13533
opened Feb 19, 2025 by
wulipc
Loading…
[API Server] Add port number range validation
frontend
ready
ONLY add when PR is ready to merge/full CI is needed
#13506
opened Feb 19, 2025 by
terrytangyuan
Loading…
[Frontend] Add environment variable to disable guided decoding fallbacks
needs-rebase
structured-output
#13505
opened Feb 19, 2025 by
joerunde
Loading…
[V1][Metrics] Implement vllm:lora_requests_info metric
v1
#13504
opened Feb 18, 2025 by
markmc
Loading…
[Misc] Warn if the vLLM version can't be retrieved
#13501
opened Feb 18, 2025 by
alex-jw-brooks
Loading…
Support SSL Key Rotation in HTTP Server
ci/build
frontend
#13495
opened Feb 18, 2025 by
youngkent
Loading…
[ToolParser] Add Qwen2.5 models tool parser
frontend
#13484
opened Feb 18, 2025 by
xiayouran
Loading…
[V1][core] Support allowed_token_ids in V1 sampler
v1
#13481
opened Feb 18, 2025 by
catherinelee274
Loading…
[CI/Build] custom build backend improvements/cleanup
ci/build
documentation
Improvements or additions to documentation
needs-rebase
[Bugfix] Initialize attention bias on the same device as Query/Key/Value
#13468
opened Feb 18, 2025 by
edwardzjl
Loading…
[Frontend] Feature: support transcription API with language detection
frontend
#13465
opened Feb 18, 2025 by
mru4913
Loading…
[Misc] Define instance attr in init and change maybe_pull_model_tokenizer_for_s3() to internal
#13443
opened Feb 18, 2025 by
terrytangyuan
Loading…
[core] MLA performance boost for AMD GPUs and tuned MoE config for MI…
rocm
#13439
opened Feb 18, 2025 by
qli88
Loading…
[Core][Feature] Input metadata dump on crash
ready
ONLY add when PR is ready to merge/full CI is needed
v1
#13407
opened Feb 17, 2025 by
wallashss
Loading…
Previous Next
ProTip!
Add no:assignee to see everything that’s not assigned.