Commits

Breadcrumbs

History for

onmain

User selector

All users

All time

Commit History

Commits on Aug 7, 2025

• feat: Update llama.cpp

  abetlen

  committed
  4f26028

  Copy full SHA for 4f26028

Commits on Jul 1, 2025

• feat: Update llama.cpp

  abetlen

  committed
  0d475d7

  Copy full SHA for 0d475d7

Commits on Jan 29, 2025

• feat: Update llama.cpp

  abetlen

  committed
  80be68a

  Copy full SHA for 80be68a

Commits on Dec 19, 2024

• feat: Update llama.cpp

  abetlen

  committed
  2bc1d97

  Copy full SHA for 2bc1d97

Commits on Oct 31, 2024

• feat: Update llama.cpp

  abetlen

  committed
  e712cff

  Copy full SHA for e712cff

Commits on Sep 19, 2024

• misc: Format

  abetlen

  committed
  9b64bb5

  Copy full SHA for 9b64bb5

• feat: Update sampling API for llama.cpp (#1742)

  Show description for f8fcb3e
  abetlen

  authored
  f8fcb3e

  Copy full SHA for f8fcb3e

Commits on Aug 15, 2024

• feat: Update llama.cpp

  abetlen

  committed
  63d65ac

  Copy full SHA for 63d65ac

Commits on Aug 4, 2024

• fix: llama_grammar_accept_token arg order (#1649)

  Show description for 5575fed
  tc-wolf

  authored
  5575fed

  Copy full SHA for 5575fed

Commits on Jul 18, 2024

• fix: Change repeat_penalty to 1.0 to match llama.cpp defaults (#1590)

  Show description for 0700476
  

  ddh0

  and

  abetlen

  authored
  0700476

  Copy full SHA for 0700476

Commits on Jul 9, 2024

• fix(minor): Minor ruff fixes

  abetlen

  committed
  08f2bb3

  Copy full SHA for 08f2bb3

• fix(misc): Format

  abetlen

  committed
  c1ae815

  Copy full SHA for c1ae815

Commits on Jul 6, 2024

• fix: update token_to_piece

  abetlen

  committed
  157d913

  Copy full SHA for 157d913

Commits on Jun 19, 2024

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

  abetlen

  committed
  4c1d74c

  Copy full SHA for 4c1d74c

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 7, 2024

• feat: Update llama.cpp

  abetlen

  committed
  255e1b4

  Copy full SHA for 255e1b4

Commits on Jun 4, 2024

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

  Show description for 027f7bc
  

  CISC

  and

  abetlen

  authored
  027f7bc

  Copy full SHA for 027f7bc

Commits on Jun 1, 2024

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

  abetlen

  committed
  af3ed50

  Copy full SHA for af3ed50

Commits on May 4, 2024

• fix: detokenization case where first token does not start with a leading space (#1375)

  Show description for e0d7674
  

  noamgat

  and

  abetlen

  authored
  e0d7674

  Copy full SHA for e0d7674

Commits on Apr 30, 2024

• fix: Suppress all logs when verbose=False, use hardcoded fileno's to work in colab notebooks. Closes #796 Closes #729

  abetlen

  committed
  f116175

  Copy full SHA for f116175

Commits on Apr 26, 2024

• feat: Allow for possibly non-pooled embeddings (#1380)

  Show description for f6ed21f
  

  iamlemec

  and

  abetlen

  authored
  f6ed21f

  Copy full SHA for f6ed21f

Commits on Apr 22, 2024

• feat: Update llama.cpp

  abetlen

  committed
  159cc4e

  Copy full SHA for 159cc4e

Commits on Apr 1, 2024

• fix: last tokens passing to sample_repetition_penalties function (#1295)

  Show description for 62aad61
  

  3 peopleauthored
  62aad61

  Copy full SHA for 62aad61

Commits on Feb 28, 2024

• fix: Remove deprecated cfg sampling functions

  abetlen

  committed
  8c71725

  Copy full SHA for 8c71725

Commits on Feb 26, 2024

• feat: Update llama.cpp

  abetlen

  committed
  cbbcd88

  Copy full SHA for cbbcd88

Commits on Feb 23, 2024

• misc: use typesafe byref for internal classes

  abetlen

  committed
  b9aca61

  Copy full SHA for b9aca61

Commits on Feb 22, 2024

• fix: Raise exceptions when llama model or context fails to load

  abetlen

  committed
  dd22010

  Copy full SHA for dd22010

Commits on Feb 21, 2024

• feat(low-level-api): Improve API static type-safety and performance (#1205)

  abetlen

  authored
  7f51b60

  Copy full SHA for 7f51b60

Commits on Feb 14, 2024

• feat: Support batch embeddings (#1186)

  Show description for d7a6791
  

  iamlemec

  and

  abetlen

  authored
  d7a6791

  Copy full SHA for d7a6791

• fix: destructor exception where internal classes are missing some uninitialized attributes

  abetlen

  committed
  6943bab

  Copy full SHA for 6943bab

Commits on Feb 6, 2024

• fix: Use llama_log_callback to avoid suppress_stdout_stderr

  abetlen

  committed
  59760c8

  Copy full SHA for 59760c8

Commits on Jan 29, 2024

• Automatically set chat format from gguf (#1110)

  Show description for da003d8
  abetlen

  authored
  da003d8

  Copy full SHA for da003d8

Commits on Jan 19, 2024

• feat: Expose gguf model metadata in metadata property

  abetlen

  committed
  5a34c57

  Copy full SHA for 5a34c57

Commits on Jan 17, 2024

• Move helper classes to _internals submodule

  abetlen

  committed
  cc4630e

  Copy full SHA for cc4630e

Loading