Skip to content
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

[Kernel] [Triton] [AMD] Adding Triton implementations awq_dequantize and awq_gemm to support AWQ #7386

Merged
merged 59 commits into from
Aug 28, 2024
Merged
Changes from 1 commit
Commits
Show all changes
59 commits
Select commit Hold shift + click to select a range
ff27ffa
Add awq_dequantize_triton
rasmith Jul 26, 2024
f9b6e74
Add awq_dequantize_triton
rasmith Jul 26, 2024
7b49a76
Merge branch 'ransmith_awq_dequantize_triton' of github.com:rasmith/v…
rasmith Jul 31, 2024
e2c3ba5
Merge branch 'vllm-project:main' into ransmith_awq_dequantize_triton
rasmith Jul 31, 2024
ec14fe9
Use any instead of all
rasmith Jul 31, 2024
fd80f7f
ruff checks
rasmith Jul 31, 2024
370c9f0
run isort
rasmith Jul 31, 2024
bdd0ab7
run yapf
rasmith Jul 31, 2024
915e0ae
Format for PR
rasmith Jul 31, 2024
3b3a563
Merge branch 'ransmith_awq_dequantize_triton' of github.com:rasmith/v…
rasmith Aug 9, 2024
150db8c
Merge branch 'vllm-project:main' into ransmith_awq_dequantize_triton
rasmith Aug 9, 2024
00dee49
Merge branch 'main' into ransmith_awq_dequantize_triton
rasmith Aug 9, 2024
a8ef8c2
Merge branch 'ransmith_awq_dequantize_triton' of github.com:rasmith/v…
rasmith Aug 9, 2024
2ebd212
Have working awq_gemm in Triton
rasmith Aug 9, 2024
e3073bc
Merge branch 'main' into ransmith_awq_gemm_triton
rasmith Aug 10, 2024
5326dde
Optimizations to awq_gemm
rasmith Aug 10, 2024
fb43aa4
Small cleanup
rasmith Aug 10, 2024
43abe7a
ruff and yapf linting/formatting
rasmith Aug 12, 2024
91c6741
isort/ruff fixing
rasmith Aug 12, 2024
962ea59
add env VLLM_USE_TRITON_AWQ
rasmith Aug 14, 2024
c9df260
Add tests
rasmith Aug 16, 2024
c7b63e8
awq for rocm in config
rasmith Aug 16, 2024
5cf14db
add dimension assertions
rasmith Aug 16, 2024
23cf001
fix typo
rasmith Aug 16, 2024
f94c1b0
yappity yapf
rasmith Aug 16, 2024
5887e77
merge main
rasmith Aug 16, 2024
8594e25
Merge branch 'vllm-project:main' into ransmith_awq_gemm_triton
rasmith Aug 16, 2024
64e5251
Merge main
rasmith Aug 16, 2024
86f2ec6
warning message for AWQ on ROCm and not setting VLLM_USE_TRITON_AWQ
rasmith Aug 19, 2024
d32212a
VLLM_USE_TRITON_AWQ enabled automatically
rasmith Aug 19, 2024
6514622
parameterized unit tests
rasmith Aug 20, 2024
8a1f6f2
cleanup
rasmith Aug 20, 2024
39d44a2
ruff
rasmith Aug 20, 2024
34e06b5
yapf
rasmith Aug 20, 2024
4f3148f
yapf
rasmith Aug 20, 2024
010c80e
Merge branch 'main' into ransmith_awq_gemm_triton
rasmith Aug 20, 2024
4895074
test cleanup
rasmith Aug 21, 2024
0e1862c
test cleanup
rasmith Aug 21, 2024
24a6b3b
yapf
rasmith Aug 21, 2024
3d2854c
merge main
rasmith Aug 22, 2024
c3b8102
Adjust threshold
rasmith Aug 22, 2024
a84c7d7
Merge branch 'main' into ransmith_awq_gemm_triton
rasmith Aug 23, 2024
c7fbacf
simplify unit test and use assert_close
rasmith Aug 24, 2024
11860d6
clean up test
rasmith Aug 24, 2024
bea93a2
Merge branch 'main' into ransmith_awq_gemm_triton
rasmith Aug 24, 2024
0c45b68
use marlin tolerance
rasmith Aug 24, 2024
bbfb4d9
update test
rasmith Aug 24, 2024
13bb612
Merge branch 'main' into ransmith_awq_gemm_triton
rasmith Aug 24, 2024
226e7fb
Merge branch 'main' into ransmith_awq_gemm_triton
rasmith Aug 24, 2024
c4e3fd1
Merge branch 'vllm-project:main' into ransmith_awq_gemm_triton
rasmith Aug 25, 2024
62612ee
Support more group sizes
rasmith Aug 26, 2024
5d91e78
Merge branch 'main' into ransmith_awq_gemm_triton
rasmith Aug 26, 2024
ba434dc
Merge branch 'ransmith_awq_gemm_triton' of github.com:rasmith/vllm in…
rasmith Aug 26, 2024
2db93e0
assert added
rasmith Aug 26, 2024
f07c241
ruff
rasmith Aug 26, 2024
e95dfc4
ruff
rasmith Aug 26, 2024
efbd8a5
isort
rasmith Aug 26, 2024
69573dd
test update
rasmith Aug 26, 2024
d456232
update comment
rasmith Aug 26, 2024
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
Merge branch 'vllm-project:main' into ransmith_awq_gemm_triton
  • Loading branch information
rasmith committed Aug 25, 2024
commit c4e3fd1f2320d16276fac884dde3ea7cebded9c0

This merge commit was added into this branch cleanly.

There are no new changes to show, but you can still view the diff.