Skip to content

Distribute and run LLMs with a single file.

Commits on main

Add Phi-3-mini-4k-instruct to README.md
Justine Tunney committed 2 years ago
b82c0ec
Release llamafile v0.8.1
Justine Tunney committed 2 years ago
2095d50
Add tool for verifying llamafile binary content
Justine Tunney committed 2 years ago
7e6a488
Use 64-bit indexing in sgemm code
Justine Tunney committed 2 years ago
e06158c
Fix the build
Justine Tunney committed 2 years ago
29e417f
Add new llamafile-tokenize command
Justine Tunney committed 2 years ago
cb9d7b3
Sync with llama.cpp upstream
Justine Tunney committed 2 years ago
208f5b4
Clamp K quant range when using f32 input
Justine Tunney committed 2 years ago
cff5512
Add more llamafiles to README.md
Justine Tunney committed 2 years ago
bebae6e
Release llamafile v0.8
Justine Tunney committed 2 years ago
82f87bd
Restore the --log-disable flag
Justine Tunney committed 2 years ago
0e2c87c
Use hack to measure prompt tok/sec in web gui
Justine Tunney committed 2 years ago
a54815e
Restore Alderlake performance
Justine Tunney committed 2 years ago
38cf08f
Restore Raspberry Pi performance
Justine Tunney committed 2 years ago
0d5a05a
Display prompt eval tokens per second in web gui
Justine Tunney committed 2 years ago
449196c
Add ability to override chat template in web gui
Justine Tunney committed 2 years ago
da5cbe4
Add HTML5 prologue to server HTML
Justine Tunney committed 2 years ago
40d6b8e
Fix stack spill caused by recent BLAS refactoring
Justine Tunney committed 2 years ago
af7aa5d
Remap <|eot_id|> → <|end_of_text|>
Justine Tunney committed 2 years ago
4a6bada
Refactor new hardware detection code
Justine Tunney committed 2 years ago
32cd7cd
Improve hardware detection
Justine Tunney committed 2 years ago
010c3e2
Make MoE prompt eval faster on CPUs
Justine Tunney committed 2 years ago
4db03a1
Fix some issues with CUDA
Justine Tunney committed 2 years ago
a49e33d
Synchronize with llama.cpp upstream
Justine Tunney committed 2 years ago
850f43d
Simplify and optimize the sgemm code
Justine Tunney committed 2 years ago
b52304e
Improve markdown and syntax highlighting in server (#88)
Dominic Szablewski committed 2 years ago
dd49f26
Create tool for slicing files >50gb
Justine Tunney committed 2 years ago
0956de7
Detect search query to start webchat (#333)
Ed Lee committed 2 years ago
a812463
Update README.md (#276)
Mahyar committed 2 years ago
739ef8f