Commits

Branch selector

 main

User selector

All users

Datepicker

All time

Commit History

Commits on Oct 6, 2025

• TPRD-1710: Update default branches post-25.09 (#99)

  Show description for f921ead
  

  mc-nv

  and

  yinggeh

  authored
  f921ead

  Copy full SHA for f921ead

Commits on Sep 24, 2025

• ci: Remove deprecated vLLM config "disable_log_requests" (#96)

  yinggeh

  authored
  2d0f250

  Copy full SHA for 2d0f250

Commits on Jul 30, 2025

• TPRD-1641: Lock package version 'transformers<=4.53.3' in test scenario due to API conflict (#94)

  mc-nv

  authored
  ed9ff01

  Copy full SHA for ed9ff01

Commits on May 8, 2025

• vLLM adjustments (#91)

  oandreeva-nv

  authored
  b41f716

  Copy full SHA for b41f716

Commits on Apr 11, 2025

• vLLM SBSA build (#86)

  oandreeva-nv

  authored
  3564c3c

  Copy full SHA for 3564c3c

Commits on Apr 2, 2025

• [fix] replacing torch.cuda.set_device with CUDA_VISIBLE_DEVICES (#85)

  oandreeva-nv

  authored
  b40fca4

  Copy full SHA for b40fca4

Commits on Mar 6, 2025

• doc: fix wrong model path in vllm_backend readme (#84)

  ziqifan617

  authored
  8960b96

  Copy full SHA for 8960b96

Commits on Feb 14, 2025

• Fixing copyrights (#83)

  oandreeva-nv

  authored
  cc88f97

  Copy full SHA for cc88f97

Commits on Feb 13, 2025

• [fix] Adjusting VllmStatLogger for 0.7.0 changes in API (#81)

  Show description for 1f36c6c
  

  oandreeva-nv

  and

  yinggeh

  authored
  1f36c6c

  Copy full SHA for 1f36c6c

Commits on Jan 9, 2025

• [fix] Sampling Parameters related improvements (#80)

  oandreeva-nv

  authored
  80dd037

  Copy full SHA for 80dd037

Commits on Dec 23, 2024

• ci: Fix L0_model_control_stress_vllm (#79)

  yinggeh

  authored
  d061556

  Copy full SHA for d061556

Commits on Dec 20, 2024

• perf: Upgrade vLLM version to 0.6.3.post1 (#76)

  Show description for 2f5bfbd
  

  kthui

  and

  oandreeva-nv

  authored
  2f5bfbd

  Copy full SHA for 2f5bfbd

Commits on Dec 5, 2024

• feat: Add log probabilities and number of input tokens to additional outputs (#75)

  Show description for 0b9c8e2
  

  kthui

  and

  rmccorm4

  authored
  0b9c8e2

  Copy full SHA for 0b9c8e2

• feat: Auto unload model if vLLM health check failed (#73)

  kthui

  authored
  b594d07

  Copy full SHA for b594d07

Commits on Nov 26, 2024

• Update `main` branch post 24.11 (#74)

  Show description for 366e668
  

  mc-nv

  and

  rmccorm4

  authored
  366e668

  Copy full SHA for 366e668

• feat: Support sending additional outputs from vLLM inference (#70)

  kthui

  authored
  ceb5961

  Copy full SHA for ceb5961

Commits on Nov 25, 2024

• Support input for llama3.2 multi-modal model (#69)

  Show description for 6c066f6
  

  xiejibing

  and

  jibxie

  authored
  6c066f6

  Copy full SHA for 6c066f6

Commits on Sep 24, 2024

• vLLM multi gpu tests adjustments (#65)

  Show description for b71088a
  

  oandreeva-nv

  and

  kthui

  authored
  b71088a

  Copy full SHA for b71088a

• fix: Adding ensemble support for vllm container (#68)

  Show description for 0df1013
  

  KrishnanPrash

  and

  rmccorm4

  authored
  0df1013

  Copy full SHA for 0df1013

Commits on Sep 21, 2024

• perf: vLLM metrics optimization (#66)

  yinggeh

  authored
  fe14385

  Copy full SHA for fe14385

Commits on Sep 4, 2024

• fix: Fix L0_backend_vllm* jobs (#62)

  yinggeh

  authored
  501f74d

  Copy full SHA for 501f74d

Commits on Aug 24, 2024

• feat: Report more histogram metrics (#61)

  yinggeh

  authored
  98947a7

  Copy full SHA for 98947a7

Commits on Aug 16, 2024

• feat: Report histogram metrics to Triton metrics server (#58)

  yinggeh

  authored
  507e4dc

  Copy full SHA for 507e4dc

• feat: Add vLLM counter metrics access through Triton (#53)

  Show description for 3829366
  yinggeh

  authored
  3829366

  Copy full SHA for 3829366

Commits on Aug 7, 2024

• perf: Check for cancellation on response thread (#54)

  Show description for 843cbdd
  

  kthui

  and

  Tabrizian

  authored
  843cbdd

  Copy full SHA for 843cbdd

Commits on Aug 6, 2024

• refactor: Remove explicit callings to garbage collect (#55)

  Show description for a345a1d
  

  kthui

  and

  nnshah1

  authored
  a345a1d

  Copy full SHA for a345a1d

Commits on Jul 26, 2024

• perf: Improve vLLM backend performance by using a separate thread for responses (#46)

  Show description for 128abc3
  

  Tabrizian

  and

  kthui

  authored
  128abc3

  Copy full SHA for 128abc3

Commits on Jul 25, 2024

• test: Limiting multi-gpu tests to use Ray as distributed_executor_backend (#47)

  oandreeva-nv

  authored
  05c5a8b

  Copy full SHA for 05c5a8b

Commits on Jul 5, 2024

• Removed explicit mode for multi-lora (#45)

  oandreeva-nv

  authored
  db3d794

  Copy full SHA for db3d794

Commits on May 31, 2024

• fix: Enhance checks around KIND_GPU and tensor parallelism (#42)

  Show description for 18a96e3
  

  rmccorm4

  and

  oandreeva-nv

  authored
  18a96e3

  Copy full SHA for 18a96e3

Commits on May 29, 2024

• Removed the note regarding 24.05 being in development (#44)

  oandreeva-nv

  authored
  2a1691a

  Copy full SHA for 2a1691a

• Update CI - Bump vllm to v0.4.2 (#43)

  pskiran1

  authored
  f77614e

  Copy full SHA for f77614e

Commits on May 2, 2024

• Tests' re-org (#39)

  oandreeva-nv

  authored
  861a198

  Copy full SHA for 861a198

Commits on Apr 26, 2024

• Milti-Lora docs follow up (#40)

  oandreeva-nv

  authored
  1dab325

  Copy full SHA for 1dab325

Commits on Apr 18, 2024

• Add multi-lora support for Triton vLLM backend (#23)

  Show description for f064eed
  

  l1cacheDell

  and

  oandreeva-nv

  authored
  f064eed

  Copy full SHA for f064eed

Pagination

Previous

Next