chore(typing): Add type checking to src/transformers/quantizers#44412
chore(typing): Add type checking to src/transformers/quantizers#44412tarekziade merged 43 commits intomainfrom
src/transformers/quantizers#44412Conversation
7f3d268 to
8049911
Compare
src/transformers/generationsrc/transformers/quantizers
|
Based on the #44233 branch |
87ac38b to
ea21220
Compare
|
|
||
|
|
||
| MIN_GPTQ_VERSION = "1.4.3" | ||
| MIN_OPTIMUM_VERSION = "1.24.0" |
There was a problem hiding this comment.
using cleaner constants, also not sure why we had 1.24.0 and 1.23.99 checks so I cleaned it up after checking optimum releases that exist
5714a08 to
b202c77
Compare
dbe048c to
ee5781d
Compare
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
vasqu
left a comment
There was a problem hiding this comment.
LGTM, thanks for iterating. Would be nice if you could take a look at the aqlm test or at least check if it was indeed broken before
9cbadfa to
7e6c53f
Compare
|
run-slow: fbgemm_fp8, finegrained_fp8, gptq, higgs, hqq, metal, mxfp4, sinq |
|
This comment contains models: [] |
CI ResultsCommit Info
The test failure analysis could not be completed. Please check the workflow run for details. |
|
run-slow: aqlm |
|
run-slow: fbgemm_fp8, finegrained_fp8, gptq, higgs, hqq, metal, mxfp4, sinq |
|
This comment contains models: [] |
CI ResultsCommit Info
The test failure analysis could not be completed. Please check the workflow run for details. |
|
run-slow: aqlm_integration |
|
This comment contains models: [] |
|
run-slow: fbgemm_fp8, finegrained_fp8, gptq, higgs, hqq, metal, mxfp4, sinq |
|
This comment contains models: [] |
Co-authored-by: vasqu
Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>
Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>
ce0ca96 to
d29ec94
Compare
|
run-slow: fbgemm_fp8, finegrained_fp8, gptq, higgs, hqq, metal, mxfp4, sinq |
|
[For maintainers] Suggested jobs to run (before merge) run-slow: fbgemm_fp8, finegrained_fp8, gptq, higgs, hqq, metal, mxfp4, sinq |
|
run-slow: fbgemm_fp8, finegrained_fp8, gptq, higgs, hqq, metal, mxfp4, sinq |
|
Workflow Run ⚙️💔 This comment contains |
|
This comment contains models: [] |
What does this PR do?
Extends type checking to
src/transformers/quantizers