Default Branch

master 41abbfd599 · qwen4exp: enable rms_norm + mul fusion (#28896) · Updated 2026-09-14 16:16:30 +02:00

ZIP  TAR.GZ

Branches

compilade/lazy-convert-hf bffdaf4010 · Merge branch 'master' into compilade/lazy-convert-hf · Updated 2024-05-08 16:56:03 +02:00    wylab	8151 26		ZIP  TAR.GZ
gg/lfs 0fc560fe96 · ci : enable git lfs for build.yml · Updated 2024-05-08 09:53:02 +02:00    wylab	8160 7		ZIP  TAR.GZ
compilade/convert-hf-refactor c32d39cefb · Merge branch 'master' into compilade/convert-hf-refactor · Updated 2024-05-06 11:33:38 +02:00    wylab	8173 19		ZIP  TAR.GZ
gg/flash-attn c240ae234c · ci : fix arg order · Updated 2024-04-30 10:43:36 +02:00    wylab	8203 145		ZIP  TAR.GZ
gg/tmp-ci 5ddad95e5c · ci : tmp disable gguf-split · Updated 2024-04-29 17:29:38 +02:00    wylab	8204 1		ZIP  TAR.GZ
gg/bpe-preprocess 80cb3127df · tests : disable test-tokenizer-1-bpe due to slowness · Updated 2024-04-29 14:24:39 +02:00    wylab	8216 61		ZIP  TAR.GZ
gg/fix-min-max 8c259f6f3e · ggml : fix MIN / MAX macros · Updated 2024-04-25 13:28:41 +02:00    wylab	8241 1		ZIP  TAR.GZ
gg/add-phi-3-support 5dcccb3a7d · convert : fix tokenizer conversion · Updated 2024-04-23 21:11:09 +02:00    wylab	8252 2		ZIP  TAR.GZ
test-bench 124e4dced2 · Update · Updated 2024-04-22 11:42:32 +02:00    wylab	8309 2		ZIP  TAR.GZ
gg/llama3-support 3750706962 · llama : add llama_token_is_eog() · Updated 2024-04-20 15:52:03 +02:00    wylab	8274 4		ZIP  TAR.GZ
gg/disable-sgemm f02ea667c1 · ggml : temporary disable llamafile sgemm until fixed · Updated 2024-04-16 21:45:56 +02:00    wylab	8283 1		ZIP  TAR.GZ
hp/tmp/kv-cache-defrag eedd42e376 · KV Cache defrag hash overflow - TMP Fix by @slaren · Updated 2024-04-16 10:24:34 +02:00    wylab	8286 1		ZIP  TAR.GZ
gg/imatrix-remove-assert 8b495540fa · imatrix : remove invalid assert · Updated 2024-04-12 10:45:12 +02:00    wylab	8311 1		ZIP  TAR.GZ
gg/authors 072e0a4d3b · scipts : add LICENSE and gen-authors.sh to sync · Updated 2024-04-09 08:19:33 +02:00    wylab	8387 3		ZIP  TAR.GZ
ceb/bert-tokenizer-fixes a37696d4f1 · speculative : more robust tokenizer comparison · Updated 2024-04-05 00:28:13 +02:00    wylab	8357 9		ZIP  TAR.GZ
gg/flash-attn-a 4c190ba676 · cuda : reduce registers · Updated 2024-03-28 20:17:08 +01:00    wylab	8399 77		ZIP  TAR.GZ
compilade/fix-command-r 64b7d85891 · llama : fix command-r inference · Updated 2024-03-28 11:22:24 +01:00    wylab	8404 1		ZIP  TAR.GZ
gg/flash-attn-wip 6be02b5969 · cuda : fix build · Updated 2024-03-27 09:31:52 +01:00    wylab	8421 72		ZIP  TAR.GZ
ceb/wpm-portable-tolower 87a6088ffe · rename unicodedata.{cpp,h} to unicode-data.{cpp,h} · Updated 2024-03-26 15:52:33 +01:00    wylab	8436 7		ZIP  TAR.GZ
ik/quantize_with_kv_overrides 9c5fd6be14 · minor : spacing · Updated 2024-03-26 13:09:02 +01:00    wylab	8434 2		ZIP  TAR.GZ