biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[ Kernel ] Enable fp8-marlin for fbgemm-fp8 models (#6606)

Browse Source
This commit is contained in:
Robert Shaw
2024-07-20 14:50:10 -04:00
committed by GitHub
parent 06d6c5fe9f
commit 9364f74eee
4 changed files with 44 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
.buildkite/lm-eval-harness/configs/Meta-Llama-3-70B-Instruct-FBGEMM-nonuniform.yaml Normal file
View File

@@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-hf-baseline.sh -m nm-testing/Meta-Llama-3-70B-Instruct-FBGEMM-nonuniform -b auto -l 1000 -f 5
model_name: "nm-testing/Meta-Llama-3-70B-Instruct-FBGEMM-nonuniform"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.905
- name: "exact_match,flexible-extract"
value: 0.905
limit: 1000
num_fewshot: 5

1
.buildkite/lm-eval-harness/configs/models-large.txt
View File

@@ -1,3 +1,4 @@
Meta-Llama-3-70B-Instruct-FBGEMM-nonuniform.yaml
Meta-Llama-3-70B-Instruct.yaml
Mixtral-8x7B-Instruct-v0.1.yaml
Qwen2-57B-A14-Instruct.yaml