[CI][ROCm] Expand weight loading test coverage on AMD and cap its KV cache (#54037)
Signed-off-by: Stefan Koncarevic <Stefan.Koncarevic@amd.com>
This commit is contained in:
@@ -1,3 +1,17 @@
|
||||
fp8, amd/Meta-Llama-3.1-8B-Instruct-FP8-KV, main
|
||||
None, amd/Llama-3.2-1B-Instruct-FP8-KV, main
|
||||
fp8, amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV, 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, gptq-8bit--1g-actorder_True
|
||||
compressed-tensors, nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change, main
|
||||
compressed-tensors, nm-testing/tinyllama-oneshot-w8-channel-a8-tensor, main
|
||||
compressed-tensors, nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2, main
|
||||
compressed-tensors, nm-testing/tinyllama-oneshot-w8a8-channel-dynamic-token-v2, main
|
||||
compressed-tensors, nm-testing/tinyllama-oneshot-w4a16-group128-v2, main
|
||||
compressed-tensors, nm-testing/tinyllama-oneshot-w8a16-per-channel, main
|
||||
compressed-tensors, nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test, main
|
||||
compressed-tensors, nm-testing/Phi-3-mini-128k-instruct-FP8, main
|
||||
compressed-tensors, neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16, main
|
||||
awq, casperhansen/mixtral-instruct-awq, main
|
||||
fp8, neuralmagic/Meta-Llama-3-8B-Instruct-FP8-KV, main
|
||||
|
||||
Reference in New Issue
Block a user