Skip to content

Activity

Showing most recent first

chore: Bump version

abetlenpushed 1 commit to main • 30ddd56…dfc9bf5 • 
6 days ago

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

Pull request merge
abetlenpushed 1 commit to main • af63792…30ddd56 • 
6 days ago

feat: Add gpt-oss chat format support through strftime_now in chat fo…

abetlenpushed 3 commits to main • 4f26028…af63792 • 
6 days ago

feat: Update llama.cpp

abetlenpushed 1 commit to main • e1af05f…4f26028 • 
6 days ago

chore: Bump version

abetlenpushed 1 commit to main • 95292e3…e1af05f • 
25 days ago

feat: Update llama.cpp

abetlenpushed 1 commit to main • d9749cb…95292e3 • 
28 days ago

chore: Bump version

abetlenpushed 1 commit to main • c8579d7…d9749cb • 
29 days ago

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

Pull request merge
abetlenpushed 1 commit to main • a99fd21…c8579d7 • 
29 days ago

feat: Update llama.cpp

abetlenpushed 1 commit to main • cce4887…a99fd21 • 
29 days ago

fix(ci): Fix macos cpu builds

abetlenpushed 1 commit to main • 8866fbd…cce4887 • 
on Jul 6

chore: Bump version

abetlenpushed 1 commit to main • 98fda8c…8866fbd • 
on Jul 6

fix(ci): Temporarily disable windows cuda wheels

abetlenpushed 1 commit to main • b39e9d4…98fda8c • 
on Jul 6

feat: Update llama.cpp

abetlenpushed 2 commits to main • 82ad829…b39e9d4 • 
on Jul 6

fix(ci): update runners for cpu builds

abetlenpushed 1 commit to main • 1580839…82ad829 • 
on Jul 5

chore: Bump version

abetlenpushed 1 commit to main • 11d28df…1580839 • 
on Jul 5

fix(ci): Remove macos-13 builds to fix cross compilation error

abetlenpushed 3 commits to main • 9e5a4ea…11d28df • 
on Jul 5

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

abetlenpushed 1 commit to main • 9770b84…9e5a4ea • 
on Jul 5

chore: Bump version

abetlenpushed 1 commit to main • 6f3f0bf…9770b84 • 
on Jul 3

docs: Add Qwen2.5-VL to README

abetlenpushed 1 commit to main • 07a979f…6f3f0bf • 
on Jul 3

fix: Use num_threads from llama model for mtmd

abetlenpushed 1 commit to main • cd548bd…07a979f • 
on Jul 3

feat: Add support for new mtmd api, add Qwen2.5-VL chat handler

abetlenpushed 1 commit to main • 0dec788…cd548bd • 
on Jul 3

fix: Fix missing deprecated symbols on windows with missing LLAMA_API…

abetlenpushed 1 commit to main • 5a635f4…0dec788 • 
on Jul 1

fix(minor): Fix type hint for older versions of python

abetlenpushed 1 commit to main • 51dce74…5a635f4 • 
on Jul 1

misc: Fix support for new parameters, deprecate rpc_servers parameter

abetlenpushed 1 commit to main • 0d475d7…51dce74 • 
on Jul 1

feat: Update llama.cpp

abetlenpushed 1 commit to main • b1d23df…0d475d7 • 
on Jul 1

hotfix: Disable curl support

abetlenpushed 1 commit to main • cb2edb9…b1d23df • 
on May 8

chore: Bump version

abetlenpushed 1 commit to main • 4c6514d…cb2edb9 • 
on May 8

feat: Update llama.cpp

abetlenpushed 1 commit to main • 99f2ebf…4c6514d • 
on May 8

feat: Update llama.cpp

abetlenpushed 1 commit to main • 37eb5f0…99f2ebf • 
on Apr 11