[ET-VK][q8ta] Add q8ta_linear_gemv op for batch-1 int8 linear #8175
metal.yml
on: pull_request
Matrix: export-model-metal-artifact
test-executorch-metal-build
/
macos-job
5m 4s
test-metal-backend-modules
/
macos-job
8m 32s
Matrix: test-model-metal-e2e
Artifacts
Produced during runtime
| Name | Size | Digest | |
|---|---|---|---|
|
mistralai-Voxtral-Mini-3B-2507-metal-non-quantized
Expired
|
6.82 GB |
sha256:8a9c961bacebe50e61b60fed3b53963c0599460a1b91b7cb58fa408ba3ebf9c1
|
|
|
mistralai-Voxtral-Mini-3B-2507-metal-quantized-int4-metal
Expired
|
3.2 GB |
sha256:0fe5efcb7932caf78959d41ee45755debef2e86d7ea8ccb8321a5d4c05b69fda
|
|
|
mistralai-Voxtral-Mini-4B-Realtime-2602-metal-quantized-int4-metal
Expired
|
16.2 GB |
sha256:a4704a30671e7f08e12e6c11f8ef2adcae35b5a45efbed1e76a24bad60fd5881
|
|
|
nvidia-parakeet-tdt-metal-non-quantized
Expired
|
951 MB |
sha256:5ab2ee90370a2875ee617fefabb9190c66881ad6c3ef7977b19124eca5d7f828
|
|
|
nvidia-parakeet-tdt-metal-quantized-int4-metal
Expired
|
436 MB |
sha256:77dc943083de0118460796f3cced047720e5fe2437665e4433babb801fef72d4
|
|
|
openai-whisper-large-v3-turbo-metal-non-quantized
Expired
|
1.18 GB |
sha256:ee3c796642a3484257c4ea9e9bd8bb69f0691368ef3667aad78afd7104df72bb
|
|
|
openai-whisper-large-v3-turbo-metal-quantized-int4-metal
Expired
|
476 MB |
sha256:02d2d66e14e0472de7e7c6ef9ef864042e273a9ca277a8aabd47f25488d17c43
|
|
|
openai-whisper-small-metal-non-quantized
Expired
|
362 MB |
sha256:0297cef79a71ad3f6f35049d2a947cab061272a64a9ac46168e92b2e23bb4a30
|
|
|
openai-whisper-small-metal-quantized-int4-metal
Expired
|
169 MB |
sha256:17de51874390ebf99db093a8163f27a48d1bc0e6b786b441759354a7cb207314
|
|