Skip to content

Pull requests: vllm-project/vllm

New pull request New
459 Open 5,308 Closed
459 Open 5,308 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[Core] Make disaggregated prefill compatible with pipeline parallelism
#12301 opened Jan 22, 2025 by YuhanLiu11 Loading…
1
[Build] update requirements of no-device ci/build
#12299 opened Jan 22, 2025 by MengqingCao Loading…
2
[V1][Frontend] Coalesce bunched RequestOutputs
#12298 opened Jan 22, 2025 by njhill Loading…
1
[Kernel] Pipe attn_logits_soft_cap through paged attention TPU kernels
#12294 opened Jan 22, 2025 by fenghuizhang Loading…
2
[Benchmark] More accurate TPOT calc in benchmark_serving.py ready ONLY add when PR is ready to merge/full CI is needed
#12288 opened Jan 22, 2025 by njhill Loading…
2
[Frontend][V1] Online serving performance improvements frontend
#12287 opened Jan 21, 2025 by njhill Loading…
11
[Core] tokens in queue metric
#12286 opened Jan 21, 2025 by annapendleton Loading…
1
[Core] Prefill Only Tokens Without KV Cache in Batch Requests (Disagg Prefill)
#12285 opened Jan 21, 2025 by Shaoting-Feng Loading…
1
[Core] Support reset_prefix_cache frontend
#12284 opened Jan 21, 2025 by comaniac Loading…
6
[AMD][Quantization] Add TritonScaledMMLinearKernel since int8 is broken for AMD
#12282 opened Jan 21, 2025 by rasmith Loading…
4
[CI/Build] Add label automation for structured-output / speculative-decoding ci/build
#12280 opened Jan 21, 2025 by russellb Loading…
1
NVIDIA Blackwell codegen ci/build documentation Improvements or additions to documentation
#12271 opened Jan 21, 2025 by johnnynunez Loading…
10
[core] separate builder init and builder prepare for each batch ready ONLY add when PR is ready to merge/full CI is needed
#12253 opened Jan 21, 2025 by youkaichao Loading…
5
[Model] Enable Inference Support for the New Baichuan-M1 Model documentation Improvements or additions to documentation new model Requests to new models
#12251 opened Jan 21, 2025 by rainkert Loading…
2
[torch.compile] decouple compile sizes and cudagraph sizes
#12243 opened Jan 21, 2025 by youkaichao Loading…
3
[Frontend] Set server's maximum number of generated tokens using generation_config.json frontend
#12242 opened Jan 21, 2025 by mhendrey Loading…
2
[Docs] Update FP8 KV Cache documentation documentation Improvements or additions to documentation
#12238 opened Jan 21, 2025 by mgoin Loading…
5
[Misc] Move find_loaded_library to platform_aware_utils.py
#12231 opened Jan 20, 2025 by houseroad Loading…
6
[VLM] Merged multi-modal processor for Pixtral
#12211 opened Jan 20, 2025 by Flechman • Draft
@DarkLight1337 @ywang96
2
[V1][Spec Decode] Ngram Spec Decode
#12193 opened Jan 19, 2025 by LiuXiaoxuanPKU • Draft
2 of 7 tasks
2
[Bugfix] fix race condition that leads to wrong order of token returned
#12192 opened Jan 19, 2025 by joennlae Loading…
3
[Misc] Add Gemma2 GGUF support
#12186 opened Jan 18, 2025 by Isotr0py • Draft
1
3
[Kernel] add triton fused moe kernel for gptq/awq
#12185 opened Jan 18, 2025 by jinzhen-lin Loading…
18
[Hardware][Gaudi][Bugfix] Fix HPU tensor parallelism, enable multiprocessing executor
#12167 opened Jan 17, 2025 by kzawora-intel Loading…
2
[Quantization/Parameter] WIP: Another Implementation of the Quantization Parameter Subclass Substitution
#12158 opened Jan 17, 2025 by cennn Loading…
3
ProTip! Mix and match filters to narrow down what you’re looking for.