Commits

Branch selector

 main

User selector

All users

Datepicker

All time

Commit History

Commits on Feb 11, 2025

• [V1][Metrics] Add GPU prefix cache hit rate % gauge (vllm-project#12592)

  comaniac

  authored
  41c5dd4

  Copy full SHA for 41c5dd4

• [Bugfix]: Reasoning output bug according to the chat template change (vllm-project#13025)

  Show description for fc6485d
  gaocegege

  authored
  fc6485d

  Copy full SHA for fc6485d

• [Misc] LoRA - Refactor Punica ops tests (vllm-project#12970)

  Show description for 78a141d
  

  varun-sundar-rabindranath

  and

  Varun Sundar Rabindranath

  authored
  78a141d

  Copy full SHA for 78a141d

• [Core] Don't do platform detection at import time (vllm-project#12933)

  Show description for c320ca8
  russellb

  authored
  c320ca8

  Copy full SHA for c320ca8

• [Benchmark] Add BurstGPT to benchmark_serving (vllm-project#13063)

  Show description for 58047c6
  

  WoosukKwon

  and

  ywang96

  authored
  58047c6

  Copy full SHA for 58047c6

• [Bugfix] Support missing tool parameters in mistral tokenizer (vllm-project#12884)

  Show description for cb080f3
  fgreinacher

  authored
  cb080f3

  Copy full SHA for cb080f3

• [Docs] Annouce Meta Meetup (vllm-project#13065)

  Show description for 2c0f582
  simon-mo

  authored
  2c0f582

  Copy full SHA for 2c0f582

• [V1][Minor] Move scheduler outputs to a separate file (vllm-project#13062)

  Show description for 2ff4857
  WoosukKwon

  authored
  2ff4857

  Copy full SHA for 2ff4857

• [misc] Fix setup.py condition to avoid AMD from being mistaken with CPU (vllm-project#13022)

  Show description for 91e8767
  khluu

  authored
  91e8767

  Copy full SHA for 91e8767

Commits on Feb 10, 2025

• [Model] Ultravox Model: Support v0.5 Release (vllm-project#12912)

  Show description for 08b2d84
  farzadab

  authored
  08b2d84

  Copy full SHA for 08b2d84

• Fix seed parameter behavior in vLLM (vllm-project#13007)

  Show description for 2ae8890
  SmartManoj

  authored
  2ae8890

  Copy full SHA for 2ae8890

• [Bugfix] Clean up and fix multi-modal processors (vllm-project#13012)

  Show description for 51f0b5f
  DarkLight1337

  authored
  51f0b5f

  Copy full SHA for 51f0b5f

• [misc] Add retries with exponential backoff for HF file existence check (vllm-project#13008)

  khluu

  authored
  fde7126

  Copy full SHA for fde7126

• [Doc] Add link to tool_choice tracking issue in tool_calling.md (vllm-project#13003)

  Show description for 2431371
  terrytangyuan

  authored
  2431371

  Copy full SHA for 2431371

• [core] fix sleep mode and pytorch checkpoint compatibility (vllm-project#13001)

  Show description for b2496bb
  youkaichao

  authored
  b2496bb

  Copy full SHA for b2496bb

• Check if selected backend is None in get_attn_backend_cls() (vllm-project#12975)

  Show description for 44607e0
  terrytangyuan

  authored
  44607e0

  Copy full SHA for 44607e0

• [V1] Use msgpack for core request serialization (vllm-project#12918)

  Show description for 67c4637
  njhill

  authored
  67c4637

  Copy full SHA for 67c4637

• [core][rlhf] add colocate example for RLHF (vllm-project#12984)

  Show description for aa0ca5e
  youkaichao

  authored
  aa0ca5e

  Copy full SHA for aa0ca5e

• [core] improve error handling when wake up from sleep mode (vllm-project#12981)

  Show description for 59fff4a
  youkaichao

  authored
  59fff4a

  Copy full SHA for 59fff4a

Commits on Feb 9, 2025

• [MISC] Always import version library first in the vllm package (vllm-project#12979)

  Show description for 29f1d47
  houseroad

  authored
  29f1d47

  Copy full SHA for 29f1d47

• [core] port pynvml into vllm codebase (vllm-project#12963)

  Show description for cf797aa
  youkaichao

  authored
  cf797aa

  Copy full SHA for cf797aa

Commits on Feb 8, 2025

• [V1] Cache uses_mrope in GPUModelRunner (vllm-project#12969)

  WoosukKwon

  authored
  24700c3

  Copy full SHA for 24700c3

• [RFC] [Mistral] FP8 format (vllm-project#10130)

  Show description for d366ccc
  

  patrickvonplaten

  and

  mgoin

  authored
  d366ccc

  Copy full SHA for d366ccc

• [V1][Minor] Remove outdated comment (vllm-project#12968)

  Show description for 870c374
  WoosukKwon

  authored
  870c374

  Copy full SHA for 870c374

• [VLM] Merged multi-modal processor for GLM4V (vllm-project#12449)

  Show description for 86222a3
  jeejeelee

  authored
  86222a3

  Copy full SHA for 86222a3

• [bugfix] fix early import of flash attention (vllm-project#12959)

  Show description for fe743b7
  youkaichao

  authored
  fe743b7

  Copy full SHA for fe743b7

• [Bugfix] Remove unused seq_group_metadata_list from ModelInputForGPU (vllm-project#12935)

  Show description for 913df14
  ShangmingCai

  authored
  913df14

  Copy full SHA for 913df14

• [CI/Build] Auto-fix Markdown files (vllm-project#12941)

  DarkLight1337

  authored
  8a69e0e

  Copy full SHA for 8a69e0e

• [Misc] Add qwen2.5-vl BNB support (vllm-project#12944)

  Isotr0py

  authored
  4c8dd12

  Copy full SHA for 4c8dd12

• [Doc] Correct HF repository for TeleChat2 models (vllm-project#12949)

  waltforme

  authored
  256a2d2

  Copy full SHA for 256a2d2

• [CI] Resolve transformers-neuronx version conflict (vllm-project#12925)

  liangfu

  authored
  c45d398

  Copy full SHA for c45d398

• [Misc] Log time consumption on weight downloading (vllm-project#12926)

  waltforme

  authored
  011e612

  Copy full SHA for 011e612

• [misc] Add LoRA to benchmark_serving (vllm-project#12898)

  Show description for 7e18376
  

  varun-sundar-rabindranath

  and

  Varun Sundar Rabindranath

  authored
  7e18376

  Copy full SHA for 7e18376

• [Hardware][Intel-Gaudi] Enable long-contexts + LoRA support for Intel Gaudi (vllm-project#12812)

  Show description for 2880e21
  SanjuCSudhakaran

  authored
  2880e21

  Copy full SHA for 2880e21

• [Build] Make pypi install work on CPU platform (vllm-project#12874)

  wangxiyuan

  authored
  407b553

  Copy full SHA for 407b553

Pagination

Previous

Next