[Quant] Consolidate GPTQ: rename gptq_marlin.py to auto_gptq.py (#38288)
Signed-off-by: Chengyi Nie <cnie@roblox.com> Co-authored-by: Chengyi Nie <cnie@roblox.com> Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
co-authored by
Chengyi Nie
Cursor
parent
3b6a204789
commit
fa2a33b893
@@ -2,7 +2,7 @@ compressed-tensors, nm-testing/Mixtral-8x7B-Instruct-v0.1-W4A16-quantized, main
|
||||
compressed-tensors, nm-testing/Mixtral-8x7B-Instruct-v0.1-W4A16-channel-quantized, main
|
||||
compressed-tensors, nm-testing/Mixtral-8x7B-Instruct-v0.1-W8A16-quantized, main
|
||||
compressed-tensors, nm-testing/test-w4a16-mixtral-actorder-group, main
|
||||
gptq_marlin, TheBloke/Mixtral-8x7B-v0.1-GPTQ, main
|
||||
gptq_marlin, TheBloke/Mixtral-8x7B-v0.1-GPTQ, gptq-8bit-128g-actorder_True
|
||||
gptq, TheBloke/Mixtral-8x7B-v0.1-GPTQ, main
|
||||
gptq, TheBloke/Mixtral-8x7B-v0.1-GPTQ, gptq-8bit-128g-actorder_True
|
||||
awq_marlin, casperhansen/deepseek-coder-v2-instruct-awq, main
|
||||
compressed-tensors, RedHatAI/Llama-4-Scout-17B-16E-Instruct-quantized.w4a16, main
|
||||
@@ -1,9 +1,3 @@
|
||||
gptq_marlin, robertgshaw2/zephyr-7b-beta-channelwise-gptq, main
|
||||
gptq_marlin, TheBloke/Llama-2-7B-GPTQ, main
|
||||
gptq_marlin, TheBloke/TinyLlama-1.1B-Chat-v1.0-GPTQ, main
|
||||
gptq_marlin, TheBloke/TinyLlama-1.1B-Chat-v1.0-GPTQ, gptq-8bit--1g-actorder_True
|
||||
gptq_marlin, TheBloke/TinyLlama-1.1B-Chat-v1.0-GPTQ, gptq-8bit-32g-actorder_True
|
||||
gptq_marlin, TechxGenus/gemma-1.1-2b-it-GPTQ, main
|
||||
gptq, robertgshaw2/zephyr-7b-beta-channelwise-gptq, main
|
||||
gptq, TheBloke/Llama-2-7B-GPTQ, main
|
||||
gptq, TheBloke/TinyLlama-1.1B-Chat-v1.0-GPTQ, main
|
||||
|
||||
Reference in New Issue
Block a user