-
-
Notifications
You must be signed in to change notification settings - Fork 7.1k
Pull requests: vllm-project/vllm
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[BugFix] Fix vllm_flash_attn install issues
ci/build
ready
ONLY add when PR is ready to merge/full CI is needed
v1
#17267
opened Apr 27, 2025 by
LucasWilkinson
Loading…
[Minor][Models] Pass partial_rotary_factor parameter to rope
#17266
opened Apr 27, 2025 by
Eviannn
Loading…
[Misc] Auto fallback to float16 for pre-Ampere GPUs when detected bfloat16 config
#17265
opened Apr 27, 2025 by
Isotr0py
Loading…
[Bugfix] Fix missing ARG in Dockerfile for arm64 platforms
ci/build
ready
ONLY add when PR is ready to merge/full CI is needed
#17261
opened Apr 27, 2025 by
lkm-schulz
Loading…
Explicitly explain quant method override ordering and ensure all overrides are ordered
quantization
#17256
opened Apr 27, 2025 by
hmellor
Loading…
Make name of Related to Google TPUs
compressed_tensors
quant method consistent across vLLM
quantization
tpu
#17255
opened Apr 27, 2025 by
hmellor
Loading…
[BUGFIX]: return fast when request requires prompt logprobs
v1
#17251
opened Apr 27, 2025 by
andyxning
Loading…
[Core] Use platform-agnostic device control for DP engine core
v1
#17245
opened Apr 27, 2025 by
jianzs
Loading…
[Docs] Add a security guide
documentation
Improvements or additions to documentation
#17230
opened Apr 26, 2025 by
russellb
Loading…
[ROCm] Effort to reduce the number of environment variables in command line
ci/build
rocm
Related to AMD ROCm
#17229
opened Apr 26, 2025 by
hongxiayang
Loading…
Use CUDA 12.6 as default for release and nightly wheels
ci/build
documentation
Improvements or additions to documentation
[Doc] Clarify note for H2O-VL
documentation
Improvements or additions to documentation
#17219
opened Apr 26, 2025 by
DarkLight1337
Loading…
[V1][Spec Decode] Apply torch.compile & cudagraph to EAGLE
documentation
Improvements or additions to documentation
v1
#17211
opened Apr 26, 2025 by
luyuzhe111
Loading…
[Misc][Tools][Benchmark] Publish script to auto tune server parameters
#17207
opened Apr 25, 2025 by
Chenyaaang
Loading…
[Benchmark] Add single turn MTBench to Serving Bench
#17202
opened Apr 25, 2025 by
ekagra-ranjan
Loading…
[Hardware][Apple] Allows VLLM_TARGET_DEVICE=empty on MacOs
ci/build
ready
ONLY add when PR is ready to merge/full CI is needed
#17200
opened Apr 25, 2025 by
wallashss
Loading…
[WIP] Support vLLM in transformers hybrid attention implementation
#17198
opened Apr 25, 2025 by
wuisawesome
Loading…
[Security] Don't bind tcp zmq socket to all interfaces
documentation
Improvements or additions to documentation
ready
ONLY add when PR is ready to merge/full CI is needed
security
Security related issues and PRs
[WIP][Bugfix] Fix 'MistralTokenizer' object has no attribute 'init_kwargs'
bug
Something isn't working
Previous Next
ProTip!
Adding no:label will show everything without a label.