Commits

Breadcrumbs

History for

ondocker

User selector

All users

All time

Commit History

Commits on Jun 21, 2024

• feat: Update llama_cpp.py bindings

  abetlen

  committed
  04959f1

  Copy full SHA for 04959f1

Commits on Jun 19, 2024

• chore: Bump version

  abetlen

  committed
  6c33190

  Copy full SHA for 6c33190

• fix: Make destructor to automatically call .close() method on Llama class.

  abetlen

  committed
  4c1d74c

  Copy full SHA for 4c1d74c

Commits on Jun 17, 2024

• feat: Update llama.cpp

  abetlen

  committed
  f4491c4

  Copy full SHA for f4491c4

Commits on Jun 13, 2024

• feat: Add `.close()` method to `Llama` class to explicitly free model from memory (#1513)

  Show description for 320a5d7
  

  jkawamoto

  and

  abetlen

  authored
  320a5d7

  Copy full SHA for 320a5d7

• feat: Support SPM infill (#1492)

  Show description for dbcf64c
  

  CISC

  and

  abetlen

  authored
  dbcf64c

  Copy full SHA for dbcf64c

Commits on Jun 10, 2024

• chore: Bump version

  abetlen

  committed
  86a38ad

  Copy full SHA for 86a38ad

Commits on Jun 7, 2024

• feat: Update llama.cpp

  abetlen

  committed
  255e1b4

  Copy full SHA for 255e1b4

Commits on Jun 4, 2024

• feat: adding `rpc_servers` parameter to `Llama` class (#1477)

  Show description for d634efc
  

  chraac

  and

  abetlen

  authored
  d634efc

  Copy full SHA for d634efc

• fix: fix logprobs when BOS is not present (#1471)

  Show description for 6e0642c
  a-ghorbani

  authored
  6e0642c

  Copy full SHA for 6e0642c

• fix: Avoid duplicate special tokens in chat formats (#1439)

  Show description for 027f7bc
  

  CISC

  and

  abetlen

  authored
  027f7bc

  Copy full SHA for 027f7bc

• chore: Bump version

  abetlen

  committed
  c3ef41b

  Copy full SHA for c3ef41b

• feat: Update llama.cpp

  abetlen

  committed
  cd3f1bb

  Copy full SHA for cd3f1bb

Commits on Jun 3, 2024

• misc: Improve llava error messages

  abetlen

  committed
  6b018e0

  Copy full SHA for 6b018e0

Commits on Jun 1, 2024

• Merge branch 'main' of https://github.com/abetlen/llama-cpp-python into main

  abetlen

  committed
  a6457ba

  Copy full SHA for a6457ba

• fix: Use numpy recarray for candidates data, fixes bug with temp < 0

  abetlen

  committed
  af3ed50

  Copy full SHA for af3ed50

Commits on May 29, 2024

• fix: Fix typo in Llama3VisionAlphaChatHandler. Closes #1488

  abetlen

  committed
  165b4dc

  Copy full SHA for 165b4dc

• fix: adjust kv_override member names to match llama.cpp

  abetlen

  committed
  91d05ab

  Copy full SHA for 91d05ab

• fix: fix string value kv_overrides. Closes #1487

  abetlen

  committed
  df45a4b

  Copy full SHA for df45a4b

Commits on May 27, 2024

• feat: Update llama.cpp

  abetlen

  committed
  454c9bb

  Copy full SHA for 454c9bb

Commits on May 24, 2024

• chore: Bump version

  abetlen

  committed
  a4c9ab8

  Copy full SHA for a4c9ab8

• feat: Improve Llama.eval performance by avoiding list conversion (#1476)

  Show description for 5cae104
  

  thoughtp0lice

  and

  abetlen

  authored
  5cae104

  Copy full SHA for 5cae104

• feat: Update llama.cpp

  abetlen

  committed
  087cc0b

  Copy full SHA for 087cc0b

Commits on May 22, 2024

• feat: Update llama.cpp

  abetlen

  committed
  5a595f0

  Copy full SHA for 5a595f0

Commits on May 16, 2024

• chore: Bump version

  abetlen

  committed
  b564d05

  Copy full SHA for b564d05

• fix: segfault for models without eos / bos tokens. Closes #1463

  abetlen

  committed
  d99a6ba

  Copy full SHA for d99a6ba

Commits on May 14, 2024

• feat: add MinTokensLogitProcessor and min_tokens argument to server (#1333)

  Show description for 5212fb0
  twaka

  authored
  5212fb0

  Copy full SHA for 5212fb0

• misc: Remove unnecessary metadata lookups (#1448)

  Show description for 389e09c
  CISC

  authored
  389e09c

  Copy full SHA for 389e09c

• Update llama.cpp

  abetlen

  committed
  50f5c74

  Copy full SHA for 50f5c74

Commits on May 12, 2024

• chore: Bump version

  abetlen

  committed
  3c19faa

  Copy full SHA for 3c19faa

Commits on May 10, 2024

• chore: Bump version

  abetlen

  committed
  7316502

  Copy full SHA for 7316502

• fix: Clear kv cache to avoid kv bug when image is evaluated first

  abetlen

  committed
  ac55d0a

  Copy full SHA for ac55d0a

• chore: Bump version

  abetlen

  committed
  4badac3

  Copy full SHA for 4badac3

• fix(security): Render all jinja templates in immutable sandbox (#1441)

  Show description for 561e880
  

  CISC

  and

  abetlen

  authored
  561e880

  Copy full SHA for 561e880

• Merge pull request from GHSA-56xg-wfcc-g829

  Show description for b454f40
  

  retr0reg

  and

  abetlen

  authored
  b454f40

  Copy full SHA for b454f40