-
-
Notifications
You must be signed in to change notification settings - Fork 4k
Issues: vllm-project/vllm
[RFC]: Reimplement and separate beam search on top of vLLM core
#8306
opened Sep 9, 2024 by
youkaichao
Open
6
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
[Misc] Create setup_files dir for cleanup
ready
ONLY add when PR is ready to merge/full CI is needed
#5673
opened Jun 19, 2024 by
WoosukKwon
Loading…
[Not for review] Spmd tp rebase
ready
ONLY add when PR is ready to merge/full CI is needed
#6483
opened Jul 16, 2024 by
ruisearch42
•
Draft
[Build/CI] Empty commit. Testing the present CI state.
ready
ONLY add when PR is ready to merge/full CI is needed
#7598
opened Aug 16, 2024 by
Alexei-V-Ivanov-AMD
Loading…
[CI/Build] Adding timeout in CPU CI to avoid CPU test queue blocking
ready
ONLY add when PR is ready to merge/full CI is needed
#6892
opened Jul 29, 2024 by
bigPYJ1151
Loading…
[ CI ] Awq Marlin Integration Tests
ready
ONLY add when PR is ready to merge/full CI is needed
#6627
opened Jul 22, 2024 by
robertgshaw2-neuralmagic
Loading…
[CI/Build] Update flashinfer to v0.0.9 (#6489)
ready
ONLY add when PR is ready to merge/full CI is needed
#6490
opened Jul 16, 2024 by
170928
Loading…
[Kernel][LoRA] Add assertion for punica sgmv kernels
ready
ONLY add when PR is ready to merge/full CI is needed
#7585
opened Aug 16, 2024 by
jeejeelee
Loading…
[Misc] Add logging for engine and executor cleanup
ready
ONLY add when PR is ready to merge/full CI is needed
#7597
opened Aug 16, 2024 by
ruisearch42
•
Draft
[Performance][Core] Optimize the performance of evictor v1 and v2 by applying a priority queue and lazy deletion
ready
ONLY add when PR is ready to merge/full CI is needed
#7209
opened Aug 6, 2024 by
llsj14
Loading…
[Multi-step] Remove redundant CPU to GPU transfer for non-last rank PP/TP
ready
ONLY add when PR is ready to merge/full CI is needed
#7715
opened Aug 21, 2024 by
SolitaryThinker
Loading…
[Model] Refactor BLIP/BLIP-2 to support composite model loading
ready
ONLY add when PR is ready to merge/full CI is needed
#8407
opened Sep 12, 2024 by
DarkLight1337
Loading…
[do-not-merge][CI/Build] Buildkite pipeline generator
ready
ONLY add when PR is ready to merge/full CI is needed
#8324
opened Sep 10, 2024 by
khluu
Loading…
[This PR is not supposed to be merged] Testing regression in Tensorizer Test
ready
ONLY add when PR is ready to merge/full CI is needed
#7927
opened Aug 27, 2024 by
Alexei-V-Ivanov-AMD
Loading…
[CI/Build] Add linting for github actions workflows
ready
ONLY add when PR is ready to merge/full CI is needed
#7876
opened Aug 26, 2024 by
russellb
Loading…
[Bugfix] Fix bug in detokenizer.py
ready
ONLY add when PR is ready to merge/full CI is needed
#8112
opened Sep 3, 2024 by
cafeii
Loading…
[Misc] Upgrade vllm-flash-attn to v2.6.2
ready
ONLY add when PR is ready to merge/full CI is needed
#8211
opened Sep 5, 2024 by
WoosukKwon
Loading…
[BugFix] Fix metrics error for --num-scheduler-steps > 1
ready
ONLY add when PR is ready to merge/full CI is needed
#8234
opened Sep 6, 2024 by
yuleil
Loading…
[Frontend] Add readiness and liveness endpoints to OpenAI API server
ready
ONLY add when PR is ready to merge/full CI is needed
#7078
opened Aug 2, 2024 by
mfournioux
Loading…
[Frontend] Add option for LLMEngine to return model hidden states.
ready
ONLY add when PR is ready to merge/full CI is needed
#7892
opened Aug 27, 2024 by
jdvin
Loading…
[CI/Build][Misc] Comparing between block manager v1 and v2, under full prefix sharing and no prefix sharing case.
ready
ONLY add when PR is ready to merge/full CI is needed
#8528
opened Sep 16, 2024 by
KuntaiDu
Loading…
Add required libcuda.so
ready
ONLY add when PR is ready to merge/full CI is needed
#6864
opened Jul 27, 2024 by
sdake
Loading…
[Core] Move detokenization to front-end process
ready
ONLY add when PR is ready to merge/full CI is needed
#7402
opened Aug 11, 2024 by
njhill
Loading…
[Kernel] Add Fused Layernorm + Dynamic-Per-Token Quant Kernels
ready
ONLY add when PR is ready to merge/full CI is needed
#6763
opened Jul 24, 2024 by
varun-sundar-rabindranath
Loading…
added bitsandbytes dependency in common requirement.txt file
ready
ONLY add when PR is ready to merge/full CI is needed
#6525
opened Jul 17, 2024 by
dipatidar
Loading…
[Core][Model] Add simple_model_runner and a new model XLMRobertaForSequenceClassification through multimodal interface
ready
ONLY add when PR is ready to merge/full CI is needed
#6260
opened Jul 9, 2024 by
AllenDou
Loading…
Previous Next
ProTip!
no:milestone will show everything without a milestone.