-
-
Notifications
You must be signed in to change notification settings - Fork 4.3k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Support int8 KVCache Quant in Vllm #1507
Commits on Oct 30, 2023
-
Lin Pengyun authored and aniz1905@gmail.com committed
Oct 30, 2023 Configuration menu - View commit details
-
Copy full SHA for ce271bc - Browse repository at this point
Copy the full SHA ce271bcView commit details -
Lin Pengyun authored and aniz1905@gmail.com committed
Oct 30, 2023 Configuration menu - View commit details
-
Copy full SHA for f8b0b05 - Browse repository at this point
Copy the full SHA f8b0b05View commit details -
Lin Pengyun authored and aniz1905@gmail.com committed
Oct 30, 2023 Configuration menu - View commit details
-
Copy full SHA for b1560db - Browse repository at this point
Copy the full SHA b1560dbView commit details -
support generating kv quant parameters and evaluting kv quant models
Lin Pengyun authored and aniz1905@gmail.com committedOct 30, 2023 Configuration menu - View commit details
-
Copy full SHA for 5c672ec - Browse repository at this point
Copy the full SHA 5c672ecView commit details -
Lin Pengyun authored and aniz1905@gmail.com committed
Oct 30, 2023 Configuration menu - View commit details
-
Copy full SHA for f8d6b99 - Browse repository at this point
Copy the full SHA f8d6b99View commit details -
Lin Pengyun authored and aniz1905@gmail.com committed
Oct 30, 2023 Configuration menu - View commit details
-
Copy full SHA for f8427e3 - Browse repository at this point
Copy the full SHA f8427e3View commit details -
aniz1905@gmail.com committed
Oct 30, 2023 Configuration menu - View commit details
-
Copy full SHA for df286fe - Browse repository at this point
Copy the full SHA df286feView commit details -
modify attention kernel test using pytest
Lin Pengyun authored and aniz1905@gmail.com committedOct 30, 2023 Configuration menu - View commit details
-
Copy full SHA for b2d9b8c - Browse repository at this point
Copy the full SHA b2d9b8cView commit details -
Lin Pengyun authored and aniz1905@gmail.com committed
Oct 30, 2023 Configuration menu - View commit details
-
Copy full SHA for c5a1a73 - Browse repository at this point
Copy the full SHA c5a1a73View commit details -
aniz1905@gmail.com committed
Oct 30, 2023 Configuration menu - View commit details
-
Copy full SHA for fbed95c - Browse repository at this point
Copy the full SHA fbed95cView commit details -
aniz1905@gmail.com committed
Oct 30, 2023 Configuration menu - View commit details
-
Copy full SHA for f396ed3 - Browse repository at this point
Copy the full SHA f396ed3View commit details
Commits on Nov 2, 2023
-
Configuration menu - View commit details
-
Copy full SHA for ad8f950 - Browse repository at this point
Copy the full SHA ad8f950View commit details
Commits on Nov 3, 2023
-
zhangpeng156 committed
Nov 3, 2023 Configuration menu - View commit details
-
Copy full SHA for 2543722 - Browse repository at this point
Copy the full SHA 2543722View commit details -
zhangpeng156 committed
Nov 3, 2023 Configuration menu - View commit details
-
Copy full SHA for 4226683 - Browse repository at this point
Copy the full SHA 4226683View commit details
Commits on Nov 15, 2023
-
aniz1905@gmail.com committed
Nov 15, 2023 Configuration menu - View commit details
-
Copy full SHA for df15d44 - Browse repository at this point
Copy the full SHA df15d44View commit details
Commits on Nov 20, 2023
-
fix reshape_and_cache_quantized
aniz1905@gmail.com committedNov 20, 2023 Configuration menu - View commit details
-
Copy full SHA for 872d156 - Browse repository at this point
Copy the full SHA 872d156View commit details
Commits on Nov 22, 2023
-
aniz1905@gmail.com committed
Nov 22, 2023 Configuration menu - View commit details
-
Copy full SHA for 8c29013 - Browse repository at this point
Copy the full SHA 8c29013View commit details -
aniz1905@gmail.com committed
Nov 22, 2023 Configuration menu - View commit details
-
Copy full SHA for 8b5278d - Browse repository at this point
Copy the full SHA 8b5278dView commit details
Commits on Nov 23, 2023
-
zhangying169 committed
Nov 23, 2023 Configuration menu - View commit details
-
Copy full SHA for d8a9d4a - Browse repository at this point
Copy the full SHA d8a9d4aView commit details -
zhangying169 committed
Nov 23, 2023 Configuration menu - View commit details
-
Copy full SHA for 0b06f96 - Browse repository at this point
Copy the full SHA 0b06f96View commit details -
zhangying169 committed
Nov 23, 2023 Configuration menu - View commit details
-
Copy full SHA for 734dcc6 - Browse repository at this point
Copy the full SHA 734dcc6View commit details
Commits on Nov 24, 2023
-
zhangpeng156 committed
Nov 24, 2023 Configuration menu - View commit details
-
Copy full SHA for 31c4083 - Browse repository at this point
Copy the full SHA 31c4083View commit details -
zhangying169 committed
Nov 24, 2023 Configuration menu - View commit details
-
Copy full SHA for 16bccc4 - Browse repository at this point
Copy the full SHA 16bccc4View commit details
Commits on Nov 27, 2023
-
zhangpeng156 committed
Nov 27, 2023 Configuration menu - View commit details
-
Copy full SHA for dd527fc - Browse repository at this point
Copy the full SHA dd527fcView commit details
Commits on Nov 29, 2023
-
aniz1905@gmail.com committed
Nov 29, 2023 Configuration menu - View commit details
-
Copy full SHA for 104fb9b - Browse repository at this point
Copy the full SHA 104fb9bView commit details
Commits on Dec 5, 2023
-
zhangying169 committed
Dec 5, 2023 Configuration menu - View commit details
-
Copy full SHA for 580566c - Browse repository at this point
Copy the full SHA 580566cView commit details
Commits on Dec 18, 2023
-
zhangying169 committed
Dec 18, 2023 Configuration menu - View commit details
-
Copy full SHA for 88ba3c0 - Browse repository at this point
Copy the full SHA 88ba3c0View commit details
Commits on Jan 16, 2024
-
Merge tag 'v0.2.7' into kv_quant_v0.2.7
zhangying169 committedJan 16, 2024 Configuration menu - View commit details
-
Copy full SHA for e2ff5a6 - Browse repository at this point
Copy the full SHA e2ff5a6View commit details -
zhangying169 committed
Jan 16, 2024 Configuration menu - View commit details
-
Copy full SHA for 3065a32 - Browse repository at this point
Copy the full SHA 3065a32View commit details -
zhangying169 committed
Jan 16, 2024 Configuration menu - View commit details
-
Copy full SHA for a896eb3 - Browse repository at this point
Copy the full SHA a896eb3View commit details
Commits on Feb 4, 2024
-
merge with remote branch 'vllm/main'
zhangying169 committedFeb 4, 2024 Configuration menu - View commit details
-
Copy full SHA for 4072871 - Browse repository at this point
Copy the full SHA 4072871View commit details
Commits on Feb 5, 2024
-
Merge branch 'kv_quant_merge' into kv_quant
zhangying169 committedFeb 5, 2024 Configuration menu - View commit details
-
Copy full SHA for c0d3895 - Browse repository at this point
Copy the full SHA c0d3895View commit details -
Merge pull request vllm-project#13 in wm_ai/project_v from tmp to kv_…
…quant - <merge-MERGE #PR-13 ~merge with remote branch 'vllm/main' >
zhangpeng156 committedFeb 5, 2024 Configuration menu - View commit details
-
Copy full SHA for f670d3c - Browse repository at this point
Copy the full SHA f670d3cView commit details -
Configuration menu - View commit details
-
Copy full SHA for 666549d - Browse repository at this point
Copy the full SHA 666549dView commit details -
zhangying169 committed
Feb 5, 2024 Configuration menu - View commit details
-
Copy full SHA for 16bb483 - Browse repository at this point
Copy the full SHA 16bb483View commit details -
zhangying169 committed
Feb 5, 2024 Configuration menu - View commit details
-
Copy full SHA for ca1fcb3 - Browse repository at this point
Copy the full SHA ca1fcb3View commit details
Commits on Feb 7, 2024
-
zhangying169 committed
Feb 7, 2024 Configuration menu - View commit details
-
Copy full SHA for 33f9d53 - Browse repository at this point
Copy the full SHA 33f9d53View commit details -
support exporting kv quant params for transformers>=4.36.0
zhangying169 committedFeb 7, 2024 Configuration menu - View commit details
-
Copy full SHA for 594ec3f - Browse repository at this point
Copy the full SHA 594ec3fView commit details -
fix benchmarks for kv cache int8
zhangying169 committedFeb 7, 2024 Configuration menu - View commit details
-
Copy full SHA for c37770b - Browse repository at this point
Copy the full SHA c37770bView commit details -
Configuration menu - View commit details
-
Copy full SHA for 815eda7 - Browse repository at this point
Copy the full SHA 815eda7View commit details -
fix supporting kv cache int8 for specified models
zhangying169 committedFeb 7, 2024 Configuration menu - View commit details
-
Copy full SHA for 14ec0ca - Browse repository at this point
Copy the full SHA 14ec0caView commit details -
zhangying169 committed
Feb 7, 2024 Configuration menu - View commit details
-
Copy full SHA for 2ff0e20 - Browse repository at this point
Copy the full SHA 2ff0e20View commit details
Commits on Feb 8, 2024
-
zhangpeng156 committed
Feb 8, 2024 Configuration menu - View commit details
-
Copy full SHA for 5744c38 - Browse repository at this point
Copy the full SHA 5744c38View commit details -
zhangpeng156 committed
Feb 8, 2024 Configuration menu - View commit details
-
Copy full SHA for cf7d939 - Browse repository at this point
Copy the full SHA cf7d939View commit details
Commits on Feb 19, 2024
-
zhangpeng156 committed
Feb 19, 2024 Configuration menu - View commit details
-
Copy full SHA for d79a96e - Browse repository at this point
Copy the full SHA d79a96eView commit details -
zhangpeng156 committed
Feb 19, 2024 Configuration menu - View commit details
-
Copy full SHA for 9a2c2c6 - Browse repository at this point
Copy the full SHA 9a2c2c6View commit details -
zhangying169 committed
Feb 19, 2024 Configuration menu - View commit details
-
Copy full SHA for b1d4ce3 - Browse repository at this point
Copy the full SHA b1d4ce3View commit details
Commits on Mar 25, 2024
-
zhangpeng156 committed
Mar 25, 2024 Configuration menu - View commit details
-
Copy full SHA for 74013b7 - Browse repository at this point
Copy the full SHA 74013b7View commit details -
zhangpeng156 committed
Mar 25, 2024 Configuration menu - View commit details
-
Copy full SHA for 128cbae - Browse repository at this point
Copy the full SHA 128cbaeView commit details
Commits on Mar 26, 2024
-
zhangpeng156 committed
Mar 26, 2024 Configuration menu - View commit details
-
Copy full SHA for e24d431 - Browse repository at this point
Copy the full SHA e24d431View commit details -
zhangpeng156 committed
Mar 26, 2024 Configuration menu - View commit details
-
Copy full SHA for 2f38a1c - Browse repository at this point
Copy the full SHA 2f38a1cView commit details -
zhangpeng156 committed
Mar 26, 2024 Configuration menu - View commit details
-
Copy full SHA for 74d706e - Browse repository at this point
Copy the full SHA 74d706eView commit details -
zhangpeng156 committed
Mar 26, 2024 Configuration menu - View commit details
-
Copy full SHA for a999930 - Browse repository at this point
Copy the full SHA a999930View commit details -
zhangpeng156 committed
Mar 26, 2024 Configuration menu - View commit details
-
Copy full SHA for 98ef941 - Browse repository at this point
Copy the full SHA 98ef941View commit details -
zhangpeng156 committed
Mar 26, 2024 Configuration menu - View commit details
-
Copy full SHA for 95f8cc7 - Browse repository at this point
Copy the full SHA 95f8cc7View commit details -
add int8_kv_cache.rst to toctree
zhangpeng156 committedMar 26, 2024 Configuration menu - View commit details
-
Copy full SHA for 02c949a - Browse repository at this point
Copy the full SHA 02c949aView commit details -
zhangying169 committed
Mar 26, 2024 Configuration menu - View commit details
-
Copy full SHA for f9fed66 - Browse repository at this point
Copy the full SHA f9fed66View commit details