Commits

Branch selector

 main

User selector

DarkLight1337

Datepicker

All time

Commit History

Commits on Sep 22, 2024

• [Model] Refactor BLIP/BLIP-2 to support composite model loading (vllm-project#8407)

  DarkLight1337

  authored
  06ed281

  Copy full SHA for 06ed281

Commits on Sep 21, 2024

• [VLM] Use SequenceData.from_token_counts to create dummy data (vllm-project#8687)

  DarkLight1337

  authored
  5e85f4f

  Copy full SHA for 5e85f4f

• [Core] Factor out common code in SequenceData and Sequence (vllm-project#8675)

  DarkLight1337

  authored
  0455c46

  Copy full SHA for 0455c46

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

  DarkLight1337

  authored
  0057894

  Copy full SHA for 0057894

Commits on Sep 20, 2024

• [Misc] Show AMD GPU topology in collect_env.py (vllm-project#8649)

  DarkLight1337

  authored
  035fa89

  Copy full SHA for 035fa89

Commits on Sep 18, 2024

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

  DarkLight1337

  authored
  6ffa3f3

  Copy full SHA for 6ffa3f3

Commits on Sep 13, 2024

• [CI/Build] Reorganize models tests (vllm-project#7820)

  DarkLight1337

  authored
  a84e598

  Copy full SHA for a84e598

• [Installation] Gate FastAPI version for Python 3.8 (vllm-project#8456)

  DarkLight1337

  authored
  ecd7a1d

  Copy full SHA for ecd7a1d

• [CI/Build] Update pixtral tests to use JSON (vllm-project#8436)

  DarkLight1337

  authored
  8427550

  Copy full SHA for 8427550

• [Bugfix] Bump fastapi and pydantic version (vllm-project#8435)

  DarkLight1337

  authored
  3f79bc3

  Copy full SHA for 3f79bc3

• [Core] Factor out input preprocessing to a separate class (vllm-project#7329)

  DarkLight1337

  authored
  5ec9c0f

  Copy full SHA for 5ec9c0f

Commits on Sep 11, 2024

• [Bugfix] Add missing attributes in mistral tokenizer (vllm-project#8364)

  DarkLight1337

  authored
  7015417

  Copy full SHA for 7015417

Commits on Sep 10, 2024

• [Frontend] Clean up type annotations for mistral tokenizer (vllm-project#8314)

  DarkLight1337

  authored
  8c054b7

  Copy full SHA for 8c054b7

• [Bugfix] Fix missing post_layernorm in CLIP (vllm-project#8155)

  DarkLight1337

  authored
  da1a844

  Copy full SHA for da1a844

Commits on Sep 7, 2024

• [Bugfix] Fix broken OpenAI tensorizer test (vllm-project#8258)

  DarkLight1337

  authored
  9f68e00

  Copy full SHA for 9f68e00

• [Model] Multi-input support for LLaVA (vllm-project#8238)

  DarkLight1337

  authored
  2f707fc

  Copy full SHA for 2f707fc

Commits on Sep 5, 2024

• [Doc] Indicate more information about supported modalities (vllm-project#8181)

  DarkLight1337

  authored
  288a938

  Copy full SHA for 288a938

Commits on Sep 4, 2024

• [Frontend] Multimodal support in offline chat (vllm-project#8098)

  DarkLight1337

  authored
  855c262

  Copy full SHA for 855c262

Commits on Aug 31, 2024

• [Bugfix] Fix import error in Phi-3.5-MoE (vllm-project#8052)

  DarkLight1337

  authored
  d05f0a9

  Copy full SHA for d05f0a9

Commits on Aug 30, 2024

• [Core] Increase default max_num_batched_tokens for multimodal models (vllm-project#8028)

  DarkLight1337

  authored
  98cef6a

  Copy full SHA for 98cef6a

• [Bugfix] Fix import error in Exaone model (vllm-project#8034)

  DarkLight1337

  authored
  afd39a4

  Copy full SHA for afd39a4

• [VLM] Disallow overflowing max_model_len for multimodal models (vllm-project#7998)

  DarkLight1337

  authored
  4abed65

  Copy full SHA for 4abed65

Commits on Aug 28, 2024

• [Bugfix][VLM] Fix incompatibility between vllm-project#7902 and vllm-project#7230 (vllm-project#7948)

  DarkLight1337

  authored
  ef9baee

  Copy full SHA for ef9baee

• [mypy][CI/Build] Fix mypy errors (vllm-project#7929)

  DarkLight1337

  authored
  51f86bf

  Copy full SHA for 51f86bf

Commits on Aug 26, 2024

• [CI/Build] Avoid downloading all HF files in RemoteOpenAIServer (vllm-project#7836)

  DarkLight1337

  authored
  029c71d

  Copy full SHA for 029c71d

Commits on Aug 21, 2024

• [mypy] Enable following imports for entrypoints (vllm-project#7248)

  Show description for baaedfd
  

  3 peopleauthored
  baaedfd

  Copy full SHA for baaedfd

Commits on Aug 14, 2024

• [VLM][Core] Support profiling with multiple multi-modal inputs per prompt (vllm-project#7126)

  DarkLight1337

  authored
  3f674a4

  Copy full SHA for 3f674a4

• [Bugfix][Docs] Update list of mock imports (vllm-project#7493)

  DarkLight1337

  authored
  dd164d7

  Copy full SHA for dd164d7

Commits on Aug 13, 2024

• [Bugfix] Fix weight loading for Chameleon when TP>1 (vllm-project#7410)

  DarkLight1337

  authored
  7025b11

  Copy full SHA for 7025b11

• [mypy] Misc. typing improvements (vllm-project#7417)

  DarkLight1337

  authored
  9ba85bc

  Copy full SHA for 9ba85bc

Commits on Aug 12, 2024

• [Core] Consolidate GB constant and enable float GB arguments (vllm-project#7416)

  DarkLight1337

  authored
  4ddc474

  Copy full SHA for 4ddc474

• [Frontend] Disallow passing model as both argument and option (vllm-project#7347)

  DarkLight1337

  authored
  24154f8

  Copy full SHA for 24154f8

Commits on Aug 9, 2024

• [Core] Support serving encoder/decoder models (vllm-project#7258)

  DarkLight1337

  authored
  7eb4a51

  Copy full SHA for 7eb4a51

Commits on Aug 7, 2024

• [Frontend] Gracefully handle missing chat template and fix CI failure (vllm-project#7238)

  Show description for 66d617e
  

  DarkLight1337

  and

  ywang96

  authored
  66d617e

  Copy full SHA for 66d617e

Commits on Aug 6, 2024

• [Model] Support SigLIP encoder and alternative decoders for LLaVA models (vllm-project#7153)

  Show description for 1f26efb
  

  DarkLight1337

  and

  ywang96

  authored
  1f26efb

  Copy full SHA for 1f26efb

Pagination

Previous

Next