Commits

Breadcrumbs

History for

onmain

User selector

All users

Datepicker

All time

Commit History

Commits on Oct 31, 2024

• feat: Update llama.cpp

  abetlen

  committed
  e712cff

  Copy full SHA for e712cff

Commits on Sep 26, 2024

• fix: Additional fixes for speculative decoding

  abetlen

  committed
  e975dab

  Copy full SHA for e975dab

• misc: Rename all_text to remaining_text (abetlen#1658)

  Show description for 11d9562
  

  xu-song

  and

  abetlen

  authored
  11d9562

  Copy full SHA for 11d9562

• fix: Fix speculative decoding

  abetlen

  committed
  9992c50

  Copy full SHA for 9992c50

Commits on Sep 20, 2024

• feat: Add option to configure n_ubatch

  abetlen

  committed
  6c44a3f

  Copy full SHA for 6c44a3f

Commits on Sep 19, 2024

• feat: Add loading sharded GGUF files from HuggingFace with Llama.from_pretrained(additional_files=[...]) . Closes abetlen#1341

  Show description for 84c0920
  

  Gnurro

  and

  abetlen

  authored
  84c0920

  Copy full SHA for 84c0920

• fix: Don't store scores internally unless logits_all=True. Reduces memory requirements for large context. Closes abetlen#1542

  abetlen

  committed
  29afcfd

  Copy full SHA for 29afcfd

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

  Show description for 22cedad
  

  xu-song

  and

  abetlen

  authored
  22cedad

  Copy full SHA for 22cedad

• misc: Format

  abetlen

  committed
  9b64bb5

  Copy full SHA for 9b64bb5

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

  Show description for f8fcb3e
  abetlen

  authored
  f8fcb3e

  Copy full SHA for f8fcb3e

Commits on Aug 31, 2024

• feat: Update llama.cpp

  abetlen

  committed
  9769e57

  Copy full SHA for 9769e57

Commits on Aug 29, 2024

• feat: Enable detokenizing special tokens with special=True (abetlen#1596)

  Show description for d981d32
  

  benniekiss

  and

  abetlen

  authored
  d981d32

  Copy full SHA for d981d32

Commits on Aug 15, 2024

• fix: Llama.close didn't free lora adapter (abetlen#1679)

  jkawamoto

  authored
  3c7501b

  Copy full SHA for 3c7501b

• feat: Update llama.cpp

  abetlen

  committed
  63d65ac

  Copy full SHA for 63d65ac

Commits on Aug 12, 2024

• fix: only print 'cache saved' in verbose mode (abetlen#1668)

  Show description for 9bab46f
  

  lsorber

  and

  abetlen

  authored
  9bab46f

  Copy full SHA for 9bab46f

Commits on Aug 8, 2024

• fix: typo

  abetlen

  committed
  7aaf701

  Copy full SHA for 7aaf701

Commits on Aug 7, 2024

• feat: Enable recursive search of HFFS.ls when using from_pretrained (abetlen#1656)

  Show description for 5e39a85
  

  benHeid

  and

  abetlen

  authored
  5e39a85

  Copy full SHA for 5e39a85

• feat: Add more detailed log for prefix-match (abetlen#1659)

  Show description for e966f3b
  

  xu-song

  and

  abetlen

  authored
  e966f3b

  Copy full SHA for e966f3b

Commits on Jul 31, 2024

• fix : Missing LoRA adapter after API change (abetlen#1630)

  shamitv

  authored
  1f0b9a2

  Copy full SHA for 1f0b9a2

Commits on Jul 18, 2024

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

  Show description for 0700476
  

  ddh0

  and

  abetlen

  authored
  0700476

  Copy full SHA for 0700476

Commits on Jul 17, 2024

• feat: Update llama.cpp

  abetlen

  committed
  7613d23

  Copy full SHA for 7613d23

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 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 (abetlen#1513)

  Show description for 320a5d7
  

  jkawamoto

  and

  abetlen

  authored
  320a5d7

  Copy full SHA for 320a5d7

• feat: Support SPM infill (abetlen#1492)

  Show description for dbcf64c
  

  CISC

  and

  abetlen

  authored
  dbcf64c

  Copy full SHA for dbcf64c

Commits on Jun 4, 2024

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

  Show description for d634efc
  

  chraac

  and

  abetlen

  authored
  d634efc

  Copy full SHA for d634efc

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

  Show description for 6e0642c
  a-ghorbani

  authored
  6e0642c

  Copy full SHA for 6e0642c

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

  Show description for 027f7bc
  

  CISC

  and

  abetlen

  authored
  027f7bc

  Copy full SHA for 027f7bc

Commits on May 29, 2024

• fix: fix string value kv_overrides. Closes abetlen#1487

  abetlen

  committed
  df45a4b

  Copy full SHA for df45a4b

Commits on May 24, 2024

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

  Show description for 5cae104
  

  thoughtp0lice

  and

  abetlen

  authored
  5cae104

  Copy full SHA for 5cae104

Commits on May 16, 2024

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

  abetlen

  committed
  d99a6ba

  Copy full SHA for d99a6ba

Commits on May 14, 2024

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

  Show description for 5212fb0
  twaka

  authored
  5212fb0

  Copy full SHA for 5212fb0

• misc: Remove unnecessary metadata lookups (abetlen#1448)

  Show description for 389e09c
  CISC

  authored
  389e09c

  Copy full SHA for 389e09c

Commits on May 9, 2024

• feat: Support multiple chat templates - step 1 (abetlen#1396)

  Show description for 5ab40e6
  

  CISC

  and

  abetlen

  authored
  5ab40e6

  Copy full SHA for 5ab40e6

Pagination

Previous

Next