Commits

Breadcrumbs

History for

on944dd8e

User selector

All users

Datepicker

All time

Commit History

Commits on Oct 17, 2024

• [Bugfix] Add random_seed to sample_hf_requests in benchmark_serving script (#9013)

  Show description for d65049d
  

  wukaixingxp

  and

  Isotr0py

  authored
  d65049d

  Copy full SHA for d65049d

• [Core] Deprecating block manager v1 and make block manager v2 default (#8704)

  Show description for 81ede99
  KuntaiDu

  authored
  81ede99

  Copy full SHA for 81ede99

Commits on Oct 16, 2024

• [Misc] Standardize RoPE handling for Qwen2-VL (#9250)

  DarkLight1337

  authored
  7e7eae3

  Copy full SHA for 7e7eae3

Commits on Oct 15, 2024

• pass ignore_eos parameter to all benchmark_serving calls (#9349)

  gracehonv

  authored
  5d264f4

  Copy full SHA for 5d264f4

Commits on Oct 11, 2024

• [Misc] Fix sampling from sonnet for long context case (#9235)

  Imss27

  authored
  94bf9ae

  Copy full SHA for 94bf9ae

Commits on Oct 10, 2024

• [Core] Add an environment variable which needs to be set explicitly to allow BlockSpaceManagerV1 (#9149)

  sroy745

  authored
  f3a507f

  Copy full SHA for f3a507f

Commits on Oct 7, 2024

• [core] remove beam search from the core (#9105)

  youkaichao

  authored
  18b296f

  Copy full SHA for 18b296f

Commits on Oct 6, 2024

• [Frontend] API support for beam search (#9087)

  Show description for 168cab6
  

  LunrEclipse

  and

  youkaichao

  authored
  168cab6

  Copy full SHA for 168cab6

Commits on Oct 4, 2024

• [Misc] Fix CI lint (#9085)

  comaniac

  authored
  27302dd

  Copy full SHA for 27302dd

• [Misc] Add random seed for prefix cache benchmark (#9081)

  Imss27

  authored
  0cc566c

  Copy full SHA for 0cc566c

• [CI] Update performance benchmark: upgrade trt-llm to r24.07, and add SGLang (#7412)

  KuntaiDu

  authored
  fbb7442

  Copy full SHA for fbb7442

Commits on Oct 1, 2024

• Update benchmark_serving.py to read and write json-datasets, results in UTF8, for better compatibility with Windows (#8997)

  vlsav

  authored
  22f5851

  Copy full SHA for 22f5851

Commits on Sep 28, 2024

• [Bugfix] Support testing prefill throughput with benchmark_serving.py --hf-output-len 1 (#8891)

  heheda12345

  authored
  e585b58

  Copy full SHA for e585b58

Commits on Sep 27, 2024

• [MISC] Fix invalid escape sequence '\' (#8830)

  Show description for 0e08875
  panpan0000

  authored
  0e08875

  Copy full SHA for 0e08875

• [Core] renamePromptInputs and inputs (#8876)

  DarkLight1337

  authored
  3b00b9c

  Copy full SHA for 3b00b9c

Commits on Sep 25, 2024

• Revert "rename PromptInputs and inputs with backward compatibility (#8760) (#8810)

  simon-mo

  authored
  4f1ba08

  Copy full SHA for 4f1ba08

• rename PromptInputs and inputs with backward compatibility (#8760)

  DarkLight1337

  authored
  28e1299

  Copy full SHA for 28e1299

• [Core] Adding Priority Scheduling (#5958)

  apatke

  authored
  6da1ab6

  Copy full SHA for 6da1ab6

Commits on Sep 24, 2024

• Revert "[Core] Rename PromptInputs to PromptType, and inputs to prompt" (#8750)

  simon-mo

  authored
  3185fb0

  Copy full SHA for 3185fb0

• re-implement beam search on top of vllm core (#8726)

  Show description for 0250dd6
  

  youkaichao

  and

  LunrEclipse

  authored
  0250dd6

  Copy full SHA for 0250dd6

Commits on Sep 23, 2024

• [Kernel] (2/N) Machete - Integrate into CompressedTensorsWNA16 and GPTQMarlin (#7701)

  Show description for 86e9c8d
  

  4 peopleauthored
  86e9c8d

  Copy full SHA for 86e9c8d

Commits on Sep 21, 2024

• [Core] Rename PromptInputs and inputs(#8673)

  DarkLight1337

  authored
  0057894

  Copy full SHA for 0057894

Commits on Sep 19, 2024

• [MISC] remove engine_use_ray in benchmark_throughput.py (#8615)

  jikunshang

  authored
  855c8ae

  Copy full SHA for 855c8ae

• [Bugfix] fixing sonnet benchmark bug in benchmark_serving.py (#8616)

  KuntaiDu

  authored
  c52ec5f

  Copy full SHA for c52ec5f

Commits on Sep 18, 2024

• [CI/Build] Update Ruff version (#8469)

  Show description for 9d104b5
  

  aarnphm

  and

  DarkLight1337

  authored
  9d104b5

  Copy full SHA for 9d104b5

• [CI/Build] Avoid CUDA initialization (#8534)

  DarkLight1337

  authored
  6ffa3f3

  Copy full SHA for 6ffa3f3

Commits on Sep 17, 2024

• [Benchmark] Support sample from HF datasets and image input for benchmark_serving (#8495)

  Isotr0py

  authored
  1b6de83

  Copy full SHA for 1b6de83

Commits on Sep 11, 2024

• [Misc] Move device options to a single place (#8322)

  akx

  authored
  8baa454

  Copy full SHA for 8baa454

Commits on Sep 7, 2024

• Enable Random Prefix Caching in Serving Profiling Tool (benchmark_serving.py) (#8241)

  wschin

  authored
  795b662

  Copy full SHA for 795b662

Commits on Sep 6, 2024

• [Frontend] Add --logprobs argument to benchmark_serving.py (#8191)

  afeldman-nm

  authored
  e5cab71

  Copy full SHA for e5cab71

Commits on Sep 4, 2024

• [MISC] Replace input token throughput with total token throughput (#8164)

  Show description for 77d9e51
  

  comaniac

  and

  mgoin

  authored
  77d9e51

  Copy full SHA for 77d9e51

• [Benchmark] Add --async-engine option to benchmark_throughput.py (#7964)

  njhill

  authored
  d4db9f5

  Copy full SHA for d4db9f5

Commits on Aug 29, 2024

• Add more percentiles and latencies (#7759)

  wschin

  authored
  0c785d3

  Copy full SHA for 0c785d3

Commits on Aug 27, 2024

• [benchmark] Update TGI version (#7917)

  philschmid

  authored
  345be0e

  Copy full SHA for 345be0e

• [Core] Asynchronous Output Processor (#7049)

  Show description for 2eedede
  

  megha95

  and

  alexm-redhat

  authored
  2eedede

  Copy full SHA for 2eedede

Pagination

Previous

Next