Skip to content

Activity

Showing most recent first

fix K-tail reducing bug between subgroups.

luweizhou2016pushed 2 commits to main • 0afd57c…57d7809 • 
7 days ago

add cm_sgemm test

usstqpushed 1 commit to main • 9b22040…0afd57c • 
10 days ago

Root cause analyze the reason.

Force push
luweizhou2016force pushed to luwei/experiment_misalignment • 6bb15f6…12603ff • 
11 days ago

update with scatter reading A in align-body loop.

luweizhou2016pushed 1 commit to luwei/experiment_misalignment • 4ae8e65…6bb15f6 • 
11 days ago

clops.lora Add 1st token misalgnment support.

luweizhou2016created luwei/experiment_misalignment • 4ae8e65 • 
11 days ago

update test_cm

usstqpushed 1 commit to main • e1d855f…9b22040 • 
12 days ago

add xetla tile usage example

luo-cheng2021pushed 1 commit to main • 5d9f7c5…e1d855f • 
12 days ago

add sycl profiling support

usstqpushed 1 commit to main • f91da06…5d9f7c5 • 
14 days ago

add rms sycl/esimd/test code

luo-cheng2021pushed 1 commit to main • f664c0f…f91da06 • 
15 days ago

Clean the code for 1st token.

luweizhou2016pushed 1 commit to main • ccef63f…f664c0f • 
17 days ago

update

usstqpushed 1 commit to amx • 80de6eb…339a291 • 
18 days ago

tput: add SLM.

luweizhou2016pushed 3 commits to main • 2333151…ccef63f • 
18 days ago

fix assembly for xe2

luo-cheng2021pushed 1 commit to main • 418d41e…2333151 • 
19 days ago

fix pybind11 version error

usstqpushed 1 commit to main • 0dfe5a5…418d41e • 
19 days ago

inline assembly example

luo-cheng2021pushed 1 commit to main • f8f96b0…0dfe5a5 • 
19 days ago

fix release build

usstqpushed 1 commit to main • 2c406af…f8f96b0 • 
20 days ago

update.

luweizhou2016pushed 1 commit to luwei/final_1st_lora • 74738ed…2618fe6 • 
20 days ago

Update the comments.

luweizhou2016pushed 1 commit to main • 1888ffb…2c406af • 
21 days ago

Add lora 1st token support when tranposedB = false.

luweizhou2016pushed 1 commit to main • 3437b06…1888ffb • 
21 days ago

Add 1st token support.

luweizhou2016pushed 1 commit to luwei/final_1st_lora • d901e6f…74738ed • 
21 days ago

amx loop unroll tests

Force push
usstqforce pushed to amx • 85a0c55…80de6eb • 
21 days ago

amx loop unroll tests

usstqpushed 1 commit to amx • bee4200…85a0c55 • 
21 days ago

add vreg role concept

usstqpushed 2 commits to amx • e0356c0…bee4200 • 
21 days ago

Final 1st test.

luweizhou2016pushed 1 commit to luwei/final_1st_lora • 81181c4…d901e6f • 
22 days ago

1st support sum and scale.

luweizhou2016created luwei/final_1st_lora • 81181c4 • 
22 days ago

Refactor 2nd and clean up for easy use.

luweizhou2016pushed 1 commit to main • 5bce990…3437b06 • 
23 days ago

add CM support

usstqpushed 1 commit to main • 86f6dbf…5bce990 • 
24 days ago

update opencl

usstqpushed 1 commit to main • 18259b1…86f6dbf • 
24 days ago

ACC ok.

luweizhou2016pushed 3 commits to luwei/test_lora_1st • 459d741…3efd215 • 
25 days ago

tput accuracy ok.

luweizhou2016pushed 1 commit to luwei/test_lora_1st • 0c78192…459d741 • 
25 days ago