Skip to content
GitLab
Explore
Sign in
Overview
Active
Stale
All
This project is mirrored from
https://github.com/mlc-ai/mlc-llm
. Pull mirroring updated
Sep 19, 2024
.
gh-pages
2223f428
·
Build at Thu Sep 19 00:19:35 UTC 2024
·
Sep 19, 2024
main
default
57f6d8c4
·
[Bench] Use OpenAI v1/completions as default (#2918)
·
Sep 18, 2024
revert-2341-pr-debug-chat-softmax
f6d623ef
·
Revert "[DebugChat] Fix DebugChat softmax function and save logits to debug f…"
·
May 14, 2024
wpl
1c66bfa2
·
[DebugChat] Fix DebugChat softmax function and save logits to debug folder (#2341)
·
May 14, 2024
remove-llava-import
2570b976
·
[Model] Remove unused import to fix lint
·
May 06, 2024
docs-api-ref
765093a3
·
[Docs] Fix API reference not displayed
·
Apr 19, 2024
docs-fix
77ba7a14
·
[Docs][Fix] Update index.md for jekyll failure
·
Apr 19, 2024
revert-2154-feat/fp8-e4m3
9b754b87
·
Revert "[Quantization] Add e4m3 mode and enable fp8 storage type (#2154)"
·
Apr 18, 2024
ios-engine
c221a09a
·
[iOS] Initial scaffolding of LLMEngine in Swift
·
Apr 14, 2024
revert-2074-patch-1
6e8d1e8e
·
Revert "Allow "mlc_llm --host" option to override host triple the model compi…"
·
Apr 10, 2024
win
901b4b3b
·
[CI] Add windows ci
·
Mar 12, 2024
flow
b1a20bb5
·
Remove deprecated prebuilts
·
Mar 11, 2024
backup-2023-03-11
b44cdc53
·
[Android] Improve perf of TIR PagedAttn kernel on Android (#1915)
·
Mar 10, 2024
backup-before-old-flow-deprecation
b44cdc53
·
[Android] Improve perf of TIR PagedAttn kernel on Android (#1915)
·
Mar 10, 2024
android-apk
d306183d
·
[Docs] Update Android APK download link
·
Mar 03, 2024
ci
bcf1e6ca
·
[CI] Add retry to scm checkout
·
Mar 02, 2024
uchar-fix
57fc2c4f
·
[Fix] Fix `u_char` for Windows build
·
Feb 27, 2024
ios
38888bd0
·
[iOS] Minor updates to iOS setup
·
Feb 22, 2024
docs
b573a6d1
·
[DOCS] polish compile models
·
Jun 18, 2023