Commits

Branch selector

 custom_rope

User selector

All users

Datepicker

All time

Commit History

Commits on Jul 15, 2023

• Merge branch main into custom_rope

  abetlen

  committed
  f0797a6

  Copy full SHA for f0797a6

Commits on Jul 10, 2023

• Add bindings for custom_rope

  randoentity

  committed
  3f8f276

  Copy full SHA for 3f8f276

Commits on Jul 9, 2023

• Bump version

  abetlen

  committed
  8e0f625

  Copy full SHA for 8e0f625

• Update changelog

  abetlen

  committed
  df3d545

  Copy full SHA for df3d545

• bugfix: truncate completion max_tokens to fit context length by default

  abetlen

  committed
  a86bfdf

  Copy full SHA for a86bfdf

• bugfix: pydantic settings missing / changed fields

  abetlen

  committed
  6f70cc4

  Copy full SHA for 6f70cc4

• Bump version

  abetlen

  committed
  0f3c474

  Copy full SHA for 0f3c474

• Update llama.cpp

  abetlen

  committed
  9aa6416

  Copy full SHA for 9aa6416

• docker: Add libopenblas to simple image

  abetlen

  committed
  99f064e

  Copy full SHA for 99f064e

• Update llama.cpp

  abetlen

  committed
  00da643

  Copy full SHA for 00da643

Commits on Jul 8, 2023

• docker: update path to dockerfile

  abetlen

  committed
  3c85c41

  Copy full SHA for 3c85c41

• docker: fix docker build action args

  abetlen

  committed
  1f5e748

  Copy full SHA for 1f5e748

• docker: update context path

  abetlen

  committed
  9e153fd

  Copy full SHA for 9e153fd

• docker: add checkout action to dockerfile

  abetlen

  committed
  5b7d766

  Copy full SHA for 5b7d766

• Update docker workflow for new simple image

  abetlen

  committed
  3a2635b

  Copy full SHA for 3a2635b

• Update changelog

  abetlen

  committed
  670fe4b

  Copy full SHA for 670fe4b

• Merge pull request #64 from jm12138/add_unlimited_max_tokens

  Show description for 2472420
  abetlen

  authored
  2472420

  Copy full SHA for 2472420

• Merge branch 'main' into add_unlimited_max_tokens

  abetlen

  authored
  5d756de

  Copy full SHA for 5d756de

• Merge pull request #456 from AgentJ-WR/patch-1

  Show description for 236c4cf
  abetlen

  authored
  236c4cf

  Copy full SHA for 236c4cf

• Merge pull request #452 from audreyfeldroy/update-macos-metal-gpu-step-4

  Show description for 7952ca5
  abetlen

  authored
  7952ca5

  Copy full SHA for 7952ca5

• Merge pull request #453 from wu-qing-157/main

  Show description for b8e0bed
  abetlen

  authored
  b8e0bed

  Copy full SHA for b8e0bed

• bugfix: fix compatibility bug with openai api on last token

  abetlen

  committed
  d6e6aad

  Copy full SHA for d6e6aad

• Format

  abetlen

  committed
  4f2b5d0

  Copy full SHA for 4f2b5d0

• Show how to adjust context window in README.md

  AgentJ-WR

  authored
  ea4fbad

  Copy full SHA for ea4fbad

• perf: convert pointer to byref

  abetlen

  committed
  34c505e

  Copy full SHA for 34c505e

• Upgrade fastapi to 0.100.0 and pydantic v2

  abetlen

  committed
  52753b7

  Copy full SHA for 52753b7

Commits on Jul 7, 2023

• perf: avoid allocating new buffers during sampling

  abetlen

  committed
  11eae75

  Copy full SHA for 11eae75

• Update llama.cpp

  abetlen

  committed
  7887376

  Copy full SHA for 7887376

• perf: assign to candidates data structure instead

  abetlen

  committed
  a14d8a9

  Copy full SHA for a14d8a9

• fix indexing token_logprobs after sorting

  wu-qing-157

  committed
  9e61661

  Copy full SHA for 9e61661

• Update macOS Metal GPU step 4

  Show description for d270ec2
  audreyfeldroy

  committed
  d270ec2

  Copy full SHA for d270ec2

• Add universal docker image

  abetlen

  committed
  ca11673

  Copy full SHA for ca11673

• Add setting to control request interruption

  abetlen

  committed
  57d8ec3

  Copy full SHA for 57d8ec3

• Update llama.cpp

  abetlen

  committed
  cc542b4

  Copy full SHA for cc542b4

• Add interruptible streaming requests for llama-cpp-python server. Closes #183

  abetlen

  committed
  4c7cdcc

  Copy full SHA for 4c7cdcc

Pagination

Previous

Next