Commits

Branch selector

 main

User selector

All users

All time

Commit History

Commits on Apr 8, 2026

• feat: Update llama.cpp to ggerganov/llama.cpp@3bd9aa1f9 (#2176)

  Show description for 1bcc5bc
  abetlen

  authored
  1bcc5bc

  Copy full SHA for 1bcc5bc

Commits on Apr 3, 2026

• chore: bump version to 0.3.20 (#2171)

  abetlen

  authored
  02d6bee

  Copy full SHA for 02d6bee

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

  Show description for 08e088c
  abetlen

  authored
  08e088c

  Copy full SHA for 08e088c

• feat: Update llama.cpp to ggerganov/llama.cpp@f49e9178767d557a522618b16ce8694f9ddac628 (#2169)

  abetlen

  authored
  100b275

  Copy full SHA for 100b275

Commits on Mar 30, 2026

• feat(server): add model-load chat_template_kwargs (#2168)

  abetlen

  authored
  7257ba9

  Copy full SHA for 7257ba9

Commits on Mar 29, 2026

• ci: publish release wheels as py3-none (#2166)

  Show description for 7613aca
  abetlen

  authored
  7613aca

  Copy full SHA for 7613aca

• fix(ci): publish distinct manylinux and musllinux cpu wheels (#2165)

  Show description for fcd932a
  abetlen

  authored
  fcd932a

  Copy full SHA for fcd932a

Commits on Mar 25, 2026

• Bump version to 0.3.19 (#2162)

  abetlen

  authored
  f54421b

  Copy full SHA for f54421b

• feat: Update llama.cpp to ggerganov/llama.cpp@c0159f9c1f874da15e94f371d136f5920b4b5335 (#2161)

  Show description for c670222
  abetlen

  authored
  c670222

  Copy full SHA for c670222

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

  Show description for ac59e5a
  abetlen

  authored
  ac59e5a

  Copy full SHA for ac59e5a

• fix(ci): reduce CUDA binary wheel size only including cubins for current arches and one PTX target for forward compatibility (#2158)

  Show description for 5f9c231
  abetlen

  authored
  5f9c231

  Copy full SHA for 5f9c231

Commits on Mar 24, 2026

• chore: bump version (#2157)

  abetlen

  authored
  d6f46a5

  Copy full SHA for d6f46a5

• feat: expose attention_type parameter in Llama.__init__ (#2143)

  Show description for 7b38c31
  

  3 peopleauthored
  7b38c31

  Copy full SHA for 7b38c31

• fix(ci): docker build workflow (#2156)

  Show description for ccc6bc0
  abetlen

  authored
  ccc6bc0

  Copy full SHA for ccc6bc0

• fix(ci): cuda wheel workflow (#2155)

  Show description for 909ebf1
  abetlen

  authored
  909ebf1

  Copy full SHA for 909ebf1

• fix(ci): release wheel workflow (#2154)

  Show description for f0391c5
  abetlen

  authored
  f0391c5

  Copy full SHA for f0391c5

Commits on Mar 23, 2026

• chore: Bump version (#2153)

  abetlen

  authored
  a6b1807

  Copy full SHA for a6b1807

• fix: Qwen 3.5 support (#2152)

  Show description for 11e7a55
  abetlen

  authored
  11e7a55

  Copy full SHA for 11e7a55

• ci: add riscv64 wheel builds to release workflow (#2139)

  Show description for e1f8ac0
  

  gounthar

  and

  abetlen

  authored
  e1f8ac0

  Copy full SHA for e1f8ac0

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

  Show description for 18aa31e
  abetlen

  authored
  18aa31e

  Copy full SHA for 18aa31e

Commits on Mar 22, 2026

• misc: Add Ruff formatting (#2148)

  Show description for a9b4a06
  abetlen

  authored
  a9b4a06

  Copy full SHA for a9b4a06

• fix(ci): Fix macos tests, support both Intel and Apple Silicon testing (#2150)

  Show description for 9f661ff
  abetlen

  authored
  9f661ff

  Copy full SHA for 9f661ff

• fix(ci): Rename `huggingface-cli` to `hf` (#2149)

  Show description for ca3b00a
  abetlen

  authored
  ca3b00a

  Copy full SHA for ca3b00a

Commits on Aug 15, 2025

• chore: Bump version

  abetlen

  committed
  c37132b

  Copy full SHA for c37132b

• feat: Update llama.cpp

  abetlen

  committed
  ce6fd8b

  Copy full SHA for ce6fd8b

Commits on Aug 7, 2025

• chore: Bump version

  abetlen

  committed
  dfc9bf5

  Copy full SHA for dfc9bf5

• fix: rename op_offloat to op_offload in llama.py (#2046)

  sergey21000

  authored
  30ddd56

  Copy full SHA for 30ddd56

• feat: Add gpt-oss chat format support through strftime_now in chat format by @iamlemec

  abetlen

  committed
  af63792

  Copy full SHA for af63792

• misc: Add Python 3.13 classifier tag

  abetlen

  committed
  68e89e8

  Copy full SHA for 68e89e8

• misc: Update pypi downloads badge

  abetlen

  committed
  d12ca47

  Copy full SHA for d12ca47

• feat: Update llama.cpp

  abetlen

  committed
  4f26028

  Copy full SHA for 4f26028

Commits on Jul 18, 2025

• chore: Bump version

  abetlen

  committed
  e1af05f

  Copy full SHA for e1af05f

Commits on Jul 16, 2025

• feat: Update llama.cpp

  abetlen

  committed
  95292e3

  Copy full SHA for 95292e3

Commits on Jul 15, 2025

• chore: Bump version

  abetlen

  committed
  d9749cb

  Copy full SHA for d9749cb

• fix: Better chat format for Qwen2.5-VL (#2040)

  alcoftTAO

  authored
  c8579d7

  Copy full SHA for c8579d7