Commits

Breadcrumbs

History for

onpatch-2

User selector

All users

All time

Commit history

Commits on May 31, 2026

• fix: avoid cleanup errors for partially initialized LlamaModel (#2173)

  Show description for fdf38b3
  

  usernames122

  and

  abetlen

  authored
  fdf38b3View commit details

  Copy full SHA for fdf38b3

  View code at this pointBrowse repository at this point

Commits on May 4, 2026

• fix(_internals): use n_tokens0 offset when enabling last-token logits in add_sequence (#2205)

  Show description for 90e8df9
  Anai-Guo

  authored
  90e8df9View commit details

  Copy full SHA for 90e8df9

  View code at this pointBrowse repository at this point

Commits on Apr 3, 2026

• fix(misc): replace deprecated llama.cpp references (#2170)

  Show description for 08e088c
  abetlen

  authored
  08e088cView commit details

  Copy full SHA for 08e088c

  View code at this pointBrowse repository at this point

Commits on Mar 25, 2026

• fix: handle embedding models without KV memory (#2160)

  Show description for ac59e5a
  abetlen

  authored
  ac59e5aView commit details

  Copy full SHA for ac59e5a

  View code at this pointBrowse repository at this point

Commits on Mar 23, 2026

• fix: Qwen 3.5 support (#2152)

  Show description for 11e7a55
  abetlen

  authored
  11e7a55View commit details

  Copy full SHA for 11e7a55

  View code at this pointBrowse repository at this point

• feat: Update llama.cpp to ggerganov/llama.cpp@49bfddeca18e62fa3d39114a23e9fcbdf8a22388 (#2151)

  Show description for 18aa31e
  abetlen

  authored
  18aa31eView commit details

  Copy full SHA for 18aa31e

  View code at this pointBrowse repository at this point

Commits on Mar 22, 2026

• misc: Add Ruff formatting (#2148)

  Show description for a9b4a06
  abetlen

  authored
  a9b4a06View commit details

  Copy full SHA for a9b4a06

  View code at this pointBrowse repository at this point

Commits on Aug 7, 2025

• feat: Update llama.cpp

  abetlen

  committed
  4f26028View commit details

  Copy full SHA for 4f26028

  View code at this pointBrowse repository at this point

Commits on Jul 1, 2025

• feat: Update llama.cpp

  abetlen

  committed
  0d475d7View commit details

  Copy full SHA for 0d475d7

  View code at this pointBrowse repository at this point

Commits on Jan 29, 2025

• feat: Update llama.cpp

  abetlen

  committed
  80be68aView commit details

  Copy full SHA for 80be68a

  View code at this pointBrowse repository at this point

Commits on Dec 19, 2024

• feat: Update llama.cpp

  abetlen

  committed
  2bc1d97View commit details

  Copy full SHA for 2bc1d97

  View code at this pointBrowse repository at this point

Commits on Oct 31, 2024

• feat: Update llama.cpp

  abetlen

  committed
  e712cffView commit details

  Copy full SHA for e712cff

  View code at this pointBrowse repository at this point

Commits on Sep 19, 2024

• misc: Format

  abetlen

  committed
  9b64bb5View commit details

  Copy full SHA for 9b64bb5

  View code at this pointBrowse repository at this point

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

  Show description for f8fcb3e
  abetlen

  authored
  f8fcb3eView commit details

  Copy full SHA for f8fcb3e

  View code at this pointBrowse repository at this point

Commits on Aug 15, 2024

• feat: Update llama.cpp

  abetlen

  committed
  63d65acView commit details

  Copy full SHA for 63d65ac

  View code at this pointBrowse repository at this point

Commits on Aug 4, 2024

• fix: llama_grammar_accept_token arg order (#1649)

  Show description for 5575fed
  tc-wolf

  authored
  5575fedView commit details

  Copy full SHA for 5575fed

  View code at this pointBrowse repository at this point

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
  0700476View commit details

  Copy full SHA for 0700476

  View code at this pointBrowse repository at this point

Commits on Jul 9, 2024

• fix(minor): Minor ruff fixes

  abetlen

  committed
  08f2bb3View commit details

  Copy full SHA for 08f2bb3

  View code at this pointBrowse repository at this point

• fix(misc): Format

  abetlen

  committed
  c1ae815View commit details

  Copy full SHA for c1ae815

  View code at this pointBrowse repository at this point

Commits on Jul 6, 2024

• fix: update token_to_piece

  abetlen

  committed
  157d913View commit details

  Copy full SHA for 157d913

  View code at this pointBrowse repository at this point

Commits on Jun 19, 2024

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

  abetlen

  committed
  4c1d74cView commit details

  Copy full SHA for 4c1d74c

  View code at this pointBrowse repository at this point

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
  320a5d7View commit details

  Copy full SHA for 320a5d7

  View code at this pointBrowse repository at this point

• feat: Support SPM infill (#1492)

  Show description for dbcf64c
  

  CISC

  and

  abetlen

  authored
  dbcf64cView commit details

  Copy full SHA for dbcf64c

  View code at this pointBrowse repository at this point

Commits on Jun 7, 2024

• feat: Update llama.cpp

  abetlen

  committed
  255e1b4View commit details

  Copy full SHA for 255e1b4

  View code at this pointBrowse repository at this point

Commits on Jun 4, 2024

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

  Show description for 027f7bc
  

  CISC

  and

  abetlen

  authored
  027f7bcView commit details

  Copy full SHA for 027f7bc

  View code at this pointBrowse repository at this point

Commits on Jun 1, 2024

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

  abetlen

  committed
  af3ed50View commit details

  Copy full SHA for af3ed50

  View code at this pointBrowse repository at this point

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
  e0d7674View commit details

  Copy full SHA for e0d7674

  View code at this pointBrowse repository at this point

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
  f116175View commit details

  Copy full SHA for f116175

  View code at this pointBrowse repository at this point

Commits on Apr 26, 2024

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

  Show description for f6ed21f
  

  iamlemec

  and

  abetlen

  authored
  f6ed21fView commit details

  Copy full SHA for f6ed21f

  View code at this pointBrowse repository at this point

Commits on Apr 22, 2024

• feat: Update llama.cpp

  abetlen

  committed
  159cc4eView commit details

  Copy full SHA for 159cc4e

  View code at this pointBrowse repository at this point

Commits on Apr 1, 2024

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

  Show description for 62aad61
  

  3 peopleauthored
  62aad61View commit details

  Copy full SHA for 62aad61

  View code at this pointBrowse repository at this point

Commits on Feb 28, 2024

• fix: Remove deprecated cfg sampling functions

  abetlen

  committed
  8c71725View commit details

  Copy full SHA for 8c71725

  View code at this pointBrowse repository at this point

Commits on Feb 26, 2024

• feat: Update llama.cpp

  abetlen

  committed
  cbbcd88View commit details

  Copy full SHA for cbbcd88

  View code at this pointBrowse repository at this point

Commits on Feb 23, 2024

• misc: use typesafe byref for internal classes

  abetlen

  committed
  b9aca61View commit details

  Copy full SHA for b9aca61

  View code at this pointBrowse repository at this point

Commits on Feb 22, 2024

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

  abetlen

  committed
  dd22010View commit details

  Copy full SHA for dd22010

  View code at this pointBrowse repository at this point