Commits

Breadcrumbs

History for

onmain

User selector

All users

Datepicker

All time

Commit History

Commits on Jan 1, 2025

• [Benchmark] Add benchmark script for CPU offloading (vllm-project#11533)

  Show description for 0c6f998
  

  ApostaC

  and

  KuntaiDu

  authored
  0c6f998

  Copy full SHA for 0c6f998

Commits on Dec 25, 2024

• [Misc] Update disaggregation benchmark scripts and test logs (vllm-project#11456)

  Show description for fc60166
  Jeffwan

  authored
  fc60166

  Copy full SHA for fc60166

Commits on Dec 19, 2024

• [misc] benchmark_throughput : Add LoRA (vllm-project#11267)

  Show description for 9835673
  

  varun-sundar-rabindranath

  and

  Varun Sundar Rabindranath

  authored
  9835673

  Copy full SHA for 9835673

Commits on Dec 18, 2024

• [Kernel]: Cutlass 2:4 Sparsity + FP8/Int8 Quant Support (vllm-project#10995)

  Show description for 60508ff
  

  5 peopleauthored
  60508ff

  Copy full SHA for 60508ff

Commits on Dec 17, 2024

• [Misc] Kernel Benchmark for RMSNorm (vllm-project#11241)

  Show description for 02222a0
  

  ywang96

  and

  BBuf

  authored
  02222a0

  Copy full SHA for 02222a0

Commits on Dec 13, 2024

• [Misc] Add tokenizer_mode param to benchmark_serving.py (vllm-project#11174)

  Show description for 238c0d9
  alexm-redhat

  authored
  238c0d9

  Copy full SHA for 238c0d9

• [torch.compile] Dynamic fp8 + rms_norm fusion (vllm-project#10906)

  Show description for 30870b4
  

  ProExpertProg

  and

  Varun Sundar Rabindranath

  authored
  30870b4

  Copy full SHA for 30870b4

Commits on Dec 4, 2024

• Benchmark serving structured output (vllm-project#10880)

  Show description for 82eb5ea
  

  xuechendi

  and

  mgoin

  authored
  82eb5ea

  Copy full SHA for 82eb5ea

• [Benchmark] Benchmark structured output with datasets (vllm-project#10557)

  Show description for 381ac93
  

  xuechendi

  and

  aarnphm

  authored
  381ac93

  Copy full SHA for 381ac93

Commits on Dec 3, 2024

• [Bugfix] Prevent benchmark_throughput.py from using duplicated random prompts (vllm-project#10753)

  mgoin

  authored
  4433195

  Copy full SHA for 4433195

Commits on Dec 2, 2024

• [Core] Implement disagg prefill by StatelessProcessGroup (vllm-project#10502)

  Show description for 0590ec3
  KuntaiDu

  authored
  0590ec3

  Copy full SHA for 0590ec3

Commits on Dec 1, 2024

• [Misc] Adding MMMU-Pro vision dataset to serving benchmark (vllm-project#10804)

  Show description for c11f172
  

  3 peopleauthored
  c11f172

  Copy full SHA for c11f172

Commits on Nov 21, 2024

• fix the issue that len(tokenizer(prompt)["input_ids"]) > prompt_len (vllm-project#10524)

  Show description for 8a93a59
  sywangyi

  authored
  8a93a59

  Copy full SHA for 8a93a59

Commits on Nov 19, 2024

• [Model][Quantization] HQQ support through Marlin kernel expansion (vllm-project#9766)

  Show description for b00b33d
  ElizaWszola

  authored
  b00b33d

  Copy full SHA for b00b33d

Commits on Nov 18, 2024

• [misc] partial prefix & random input generation benchmark (vllm-project#9929)

  Show description for 90a6c75
  rickyyx

  authored
  90a6c75

  Copy full SHA for 90a6c75

• [Kernel] Initial Machete W4A8 support + Refactors (vllm-project#9855)

  Show description for 96d999f
  LucasWilkinson

  authored
  96d999f

  Copy full SHA for 96d999f

Commits on Nov 16, 2024

• [Misc] Update benchmark to support image_url file or http (vllm-project#10287)

  Show description for 8b6725b
  kakao-steve-ai

  authored
  8b6725b

  Copy full SHA for 8b6725b

Commits on Nov 8, 2024

• [Misc] Fix typo in vllm-project#5895 (vllm-project#10145)

  Show description for f4c2187
  DarkLight1337

  authored
  f4c2187

  Copy full SHA for f4c2187

• [Bugfix] Add error handling when server cannot respond any valid tokens (vllm-project#5895)

  DearPlanet

  authored
  ad39bd6

  Copy full SHA for ad39bd6

• [V1] Prefix caching (take 2) (vllm-project#9972)

  Show description for 201fc07
  comaniac

  authored
  201fc07

  Copy full SHA for 201fc07

Commits on Nov 7, 2024

• [CI/Build] Add shell script linting using shellcheck (vllm-project#7925)

  Show description for 3be5b26
  russellb

  authored
  3be5b26

  Copy full SHA for 3be5b26

• [Misc] Add Gamma-Distribution Request Generation Support for Serving Benchmark. (vllm-project#10105)

  Show description for a62bc01
  

  spliii

  and

  ywang96

  authored
  a62bc01

  Copy full SHA for a62bc01

Commits on Nov 6, 2024

• [CI/Build] drop support for Python 3.8 EOL (vllm-project#8464)

  Show description for 21063c1
  aarnphm

  authored
  21063c1

  Copy full SHA for 21063c1

Commits on Nov 5, 2024

• [Feature] Update benchmark_throughput.py to support image input (vllm-project#9851)

  Show description for d2e8033
  

  lk-chen

  and

  Linkun Chen

  authored
  d2e8033

  Copy full SHA for d2e8033

Commits on Nov 4, 2024

• [Misc] Refactor benchmark_throughput.py (vllm-project#9779)

  Show description for 9a5664d
  

  3 peopleauthored
  9a5664d

  Copy full SHA for 9a5664d

• [Bugfix] Fix E2EL mean and median stats (vllm-project#9984)

  Show description for ea4aded
  daitran2k1

  authored
  ea4aded

  Copy full SHA for ea4aded

Commits on Oct 31, 2024

• [Misc][OpenAI] deprecate max_tokens in favor of new max_completion_tokens field for chat completion endpoint (vllm-project#9837)

  gcalmettes

  authored
  abbfb61

  Copy full SHA for abbfb61

Commits on Oct 29, 2024

• [Hardware] using current_platform.seed_everything (vllm-project#9785)

  Show description for 622b7ab
  wangshuai09

  authored
  622b7ab

  Copy full SHA for 622b7ab

Commits on Oct 28, 2024

• [torch.compile] support moe models (vllm-project#9632)

  Show description for 32176fe
  youkaichao

  authored
  32176fe

  Copy full SHA for 32176fe

Commits on Oct 23, 2024

• [Misc] Separate total and output tokens in benchmark_throughput.py (vllm-project#8914)

  mgoin

  authored
  fd0e2cf

  Copy full SHA for fd0e2cf

• [Bugfix] Generate exactly input_len tokens in benchmark_throughput (vllm-project#9592)

  heheda12345

  authored
  65050a4

  Copy full SHA for 65050a4

Commits on Oct 22, 2024

• [Misc] Make benchmarks use EngineArgs (vllm-project#9529)

  JArnoldAMD

  authored
  cb6fdaa

  Copy full SHA for cb6fdaa

Commits on Oct 20, 2024

• [Frontend][Misc] Goodput metric support (vllm-project#9338)

  Imss27

  authored
  855e0e6

  Copy full SHA for 855e0e6

Commits on Oct 18, 2024

• [Misc] benchmark: Add option to set max concurrency (vllm-project#9390)

  Show description for 7dbe738
  russellb

  authored
  7dbe738

  Copy full SHA for 7dbe738

Commits on Oct 17, 2024

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

  Show description for d65049d
  

  wukaixingxp

  and

  Isotr0py

  authored
  d65049d

  Copy full SHA for d65049d

Pagination

Previous

Next