Commits

Breadcrumbs

History for

onmain

User selector

All users

All time

Commit History

Commits on Feb 23, 2026

• test: skip if insufficient resources on macOS

  

  lsorber

  authored and

  XyLearningProgramming

  committed
  ffed3ed

  Copy full SHA for ffed3ed

• feat: add streaming tool use

  

  lsorber

  authored and

  XyLearningProgramming

  committed
  d0fc814

  Copy full SHA for d0fc814

Commits on Jul 5, 2025

• fix: Update reference to in Llama.embed. Closes #2037

  abetlen

  committed
  9e5a4ea

  Copy full SHA for 9e5a4ea

Commits on Sep 19, 2024

• fix: Fix memory allocation of ndarray (#1704)

  Show description for 22cedad
  

  xu-song

  and

  abetlen

  authored
  22cedad

  Copy full SHA for 22cedad

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

  Show description for f8fcb3e
  abetlen

  authored
  f8fcb3e

  Copy full SHA for f8fcb3e

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 Apr 30, 2024

• feat: Update llama.cpp

  abetlen

  committed
  97fb860

  Copy full SHA for 97fb860

Commits on Feb 26, 2024

• feat: Update llama.cpp

  abetlen

  committed
  cbbcd88

  Copy full SHA for cbbcd88

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 8, 2024

• misc: rename grammar test

  abetlen

  committed
  2ef7ba3

  Copy full SHA for 2ef7ba3

Commits on Jan 31, 2024

• Add speculative decoding (#1120)

  Show description for fb762a6
  abetlen

  authored
  fb762a6

  Copy full SHA for fb762a6

Commits on Jan 29, 2024

• Add chat format test.

  abetlen

  committed
  9ae5819

  Copy full SHA for 9ae5819

Commits on Jan 22, 2024

• fix: from_json_schema oneof/anyof bug. Closes #1097

  abetlen

  committed
  d3f5528

  Copy full SHA for d3f5528

Commits on Jan 19, 2024

• feat: Add ability to load chat format from huggingface autotokenizer or tokenizer_config.json files.

  abetlen

  committed
  b8fc1c7

  Copy full SHA for b8fc1c7

Commits on Jan 17, 2024

• Integration of Jinja2 Templating (#875)

  Show description for 6bfe98b
  teleprint-me

  authored
  6bfe98b

  Copy full SHA for 6bfe98b

Commits on Jan 15, 2024

• Fix Pydantic model parsing (#1087)

  DeNeutoy

  authored
  c689ccc

  Copy full SHA for c689ccc

Commits on Dec 16, 2023

• Fix logits_to_logprobs for 2-D and 3-D logits (#1002)

  Show description for 5a89446
  kddubey

  authored
  5a89446

  Copy full SHA for 5a89446

Commits on Nov 22, 2023

• tests: add mock_kv_cache placeholder functions

  abetlen

  committed
  9515467

  Copy full SHA for 9515467

• tests: avoid constantly reallocating logits

  abetlen

  committed
  0ea2444

  Copy full SHA for 0ea2444

• tests: don't mock sampling functions

  abetlen

  committed
  0a7e05b

  Copy full SHA for 0a7e05b

Commits on Nov 21, 2023

• Use mock_llama for all tests

  abetlen

  committed
  d7388f1

  Copy full SHA for d7388f1

• Do not set `grammar` to `None` for new `LlamaGrammar` objects (#834)

  Show description for c21edb6
  mthuurne

  authored
  c21edb6

  Copy full SHA for c21edb6

• tests: Improve llama.cpp mock

  abetlen

  committed
  3dc21b2

  Copy full SHA for 3dc21b2

Commits on Nov 20, 2023

• Update llama.cpp

  abetlen

  committed
  2c2afa3

  Copy full SHA for 2c2afa3

Commits on Nov 10, 2023

• Fix tests

  abetlen

  committed
  e32ecb0

  Copy full SHA for e32ecb0

Commits on Nov 6, 2023

• Refactor Llama class internals

  abetlen

  committed
  e214a58

  Copy full SHA for e214a58

Commits on Nov 3, 2023

• Migrate inference to llama_batch and llama_decode api (#795)

  Show description for ab028cb
  

  abetlen

  and

  antoine-lizee

  authored
  ab028cb

  Copy full SHA for ab028cb

Commits on Nov 2, 2023

• fix: tokenization of special characters: (#850)

  Show description for 4d4e0f1
  

  antoine-lizee

  authored and

  abetlen

  committed
  4d4e0f1

  Copy full SHA for 4d4e0f1

Commits on Oct 19, 2023

• Enable finish reason tests

  abetlen

  committed
  ef03d77

  Copy full SHA for ef03d77

• Re-enable tests completion function

  abetlen

  committed
  cbeef36

  Copy full SHA for cbeef36

Commits on Sep 29, 2023

• Update llama.cpp

  abetlen

  committed
  1a1c3dc

  Copy full SHA for 1a1c3dc

Commits on Sep 5, 2023

• add test to see if llama_cpp.__version__ exists

  janvdp

  committed
  f49b6d7

  Copy full SHA for f49b6d7

Commits on Aug 27, 2023

• Update llama.cpp

  abetlen

  committed
  4887973

  Copy full SHA for 4887973

• Update llama.cpp

  abetlen

  committed
  3a29d65

  Copy full SHA for 3a29d65

Commits on Aug 25, 2023

• Strip leading space when de-tokenizing.

  abetlen

  committed
  8ac5946

  Copy full SHA for 8ac5946