20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Add missing kernel for CodeLlama-34B on A/H100 (no tensor parallelism) when using Multi-LoRA. (#3350)

Browse Source
This commit is contained in:
Or Sharir 2024-03-13 21:18:25 +02:00 committed by GitHub
parent 739c350c19
commit ae0ccb4017
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
csrc/punica/bgmv/bgmv_config.h
View File

@ -43,6 +43,7 @@ void bgmv_kernel(out_T *__restrict__ Y, const in_T *__restrict__ X,
f(in_T, out_T, W_T, narrow, 14336) \ f(in_T, out_T, W_T, narrow, 14336) \
f(in_T, out_T, W_T, narrow, 16384) \ f(in_T, out_T, W_T, narrow, 16384) \
f(in_T, out_T, W_T, narrow, 20480) \ f(in_T, out_T, W_T, narrow, 20480) \
f(in_T, out_T, W_T, narrow, 22016) \
f(in_T, out_T, W_T, narrow, 24576) \ f(in_T, out_T, W_T, narrow, 24576) \
f(in_T, out_T, W_T, narrow, 28672) \ f(in_T, out_T, W_T, narrow, 28672) \
f(in_T, out_T, W_T, narrow, 32000) \ f(in_T, out_T, W_T, narrow, 32000) \

2
tests/lora/test_punica.py
View File

@ -45,7 +45,7 @@ def _lora_ref_impl(
H1 = H2 = [ H1 = H2 = [
128, 256, 512, 1024, 1280, 2048, 2560, 2752, 3072, 3456, 3584, 4096, 5120, 128, 256, 512, 1024, 1280, 2048, 2560, 2752, 3072, 3456, 3584, 4096, 5120,
5504, 5632, 6144, 6912, 7168, 8192, 9216, 10240, 11008, 13824, 14336, 5504, 5632, 6144, 6912, 7168, 8192, 9216, 10240, 11008, 13824, 14336,
24576, 32000, 32256, 32512, 32768, 33024 22016, 24576, 32000, 32256, 32512, 32768, 33024
] ]
SEED = [0xabcdabcd987] SEED = [0xabcdabcd987]