Commits

Branch selector

 main

User selector

jikunshang

Datepicker

All time

Commit History

Commits on Feb 2, 2025

• [Hardware][Intel GPU] add XPU bf16 support (vllm-project#12392)

  Show description for f256ebe
  jikunshang

  authored
  f256ebe

  Copy full SHA for f256ebe

Commits on Jan 17, 2025

• [Bugfix] Mistral tokenizer encode accept list of str (vllm-project#12149)

  Show description for 54cacf0
  jikunshang

  authored
  54cacf0

  Copy full SHA for 54cacf0

• [CI]add genai-perf benchmark in nightly benchmark (vllm-project#10704)

  Show description for fead53b
  jikunshang

  authored
  fead53b

  Copy full SHA for fead53b

Commits on Jan 10, 2025

• [BUGFIX] Fix UnspecifiedPlatform package name (vllm-project#11916)

  Show description for 61af633
  jikunshang

  authored
  61af633

  Copy full SHA for 61af633

Commits on Jan 4, 2025

• [V1] Add RayExecutor support for AsyncLLM (api server) (vllm-project#11712)

  jikunshang

  authored
  fbf2564

  Copy full SHA for fbf2564

Commits on Dec 18, 2024

• [FIX] update openai version (vllm-project#11287)

  Show description for f954fe0
  jikunshang

  authored
  f954fe0

  Copy full SHA for f954fe0

Commits on Nov 27, 2024

• [Hardware][Gaudi]add get_name method for HPUAttentionBackend (vllm-project#10667)

  Show description for e85250b
  jikunshang

  authored
  e85250b

  Copy full SHA for e85250b

Commits on Nov 26, 2024

• [V1] Enable profile for LLMEngine (vllm-project#10665)

  jikunshang

  authored
  1f6584e

  Copy full SHA for 1f6584e

Commits on Nov 17, 2024

• [Hardware] [HPU]add mark_step for hpu (vllm-project#10239)

  Show description for 76aab90
  jikunshang

  authored
  76aab90

  Copy full SHA for 76aab90

Commits on Oct 14, 2024

• [Hardware][intel GPU] add async output process for xpu (vllm-project#8897)

  jikunshang

  authored
  4141608

  Copy full SHA for 4141608

Commits on Oct 8, 2024

• [Intel GPU] Fix xpu decode input (vllm-project#9145)

  jikunshang

  authored
  80b57f0

  Copy full SHA for 80b57f0

Commits on Sep 21, 2024

• [MISC] add support custom_op check (vllm-project#8557)

  Show description for d4bf085
  

  jikunshang

  and

  youkaichao

  authored
  d4bf085

  Copy full SHA for d4bf085

Commits on Sep 19, 2024

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

  jikunshang

  authored
  855c8ae

  Copy full SHA for 855c8ae

Commits on Sep 13, 2024

• [Hardware][intel GPU] bump up ipex version to 2.3 (vllm-project#8365)

  Show description for 8517252
  

  jikunshang

  and

  yma11

  authored
  8517252

  Copy full SHA for 8517252

Commits on Aug 27, 2024

• [Hardware][Intel GPU] Add intel GPU pipeline parallel support. (vllm-project#7810)

  jikunshang

  authored
  076169f

  Copy full SHA for 076169f

Commits on Aug 23, 2024

• [Hardware][Intel GPU] refactor xpu_model_runner for tp (vllm-project#7712)

  jikunshang

  authored
  fc5ebbd

  Copy full SHA for fc5ebbd

Commits on Aug 20, 2024

• [Intel GPU] fix xpu not support punica kernel (which use torch.library.custom_op) (vllm-project#7685)

  jikunshang

  authored
  6e4658c

  Copy full SHA for 6e4658c

• [Hardware] [Intel GPU] refactor xpu worker/executor (vllm-project#7686)

  jikunshang

  authored
  c42590f

  Copy full SHA for c42590f

• [Core] Refactor executor classes for easier inheritance (vllm-project#7673)

  Show description for b6f99a6
  jikunshang

  authored
  b6f99a6

  Copy full SHA for b6f99a6

Commits on Aug 19, 2024

• [Bugfix] Fix xpu build (vllm-project#7644)

  jikunshang

  authored
  1a36287

  Copy full SHA for 1a36287

Commits on Jun 22, 2024

• [CI][Hardware][Intel GPU] add Intel GPU(XPU) ci pipeline (vllm-project#5616)

  jikunshang

  authored
  cf90ae0

  Copy full SHA for cf90ae0

Commits on Jun 17, 2024

• [Hardware][Intel GPU] Add Intel GPU(XPU) inference backend (vllm-project#3814)

  Show description for 728c4c8
  

  3 peopleauthored
  728c4c8

  Copy full SHA for 728c4c8

Commits on May 10, 2024

• [Core]fix type annotation for swap_blocks (vllm-project#4726)

  jikunshang

  authored
  64b77df

  Copy full SHA for 64b77df

Commits on Apr 30, 2024

• [Core]Refactor gptq_marlin ops (vllm-project#4466)

  jikunshang

  authored
  26f2fb5

  Copy full SHA for 26f2fb5

Commits on Apr 25, 2024

• [Core]refactor aqlm quant ops (vllm-project#4351)

  jikunshang

  authored
  f4bc4de

  Copy full SHA for f4bc4de

Commits on Apr 11, 2024

• [Misc] Add indirection layer for custom ops (vllm-project#3913)

  jikunshang

  authored
  e9da5a4

  Copy full SHA for e9da5a4

Commits on Mar 25, 2024

• [BugFix] tensor.get_device() -> tensor.device (vllm-project#3604)

  jikunshang

  authored
  6d93d35

  Copy full SHA for 6d93d35

Commits on Feb 1, 2024

• Remove hardcoded device="cuda" to support more devices (vllm-project#2503)

  Show description for 96b6f47
  

  jikunshang

  and

  bigPYJ1151

  authored
  96b6f47

  Copy full SHA for 96b6f47