32 Commits
Author SHA1 Message Date
djramicandAndreas Karatzas 9c778e9ff8 [Bugfix][EPLB] Wait for pending expert buffer copies before NIXL READs (#62081)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
2026-10-17 18:18:02 -05:00
djramic 307c5844ad [ROCm][CI] Enable batch invariance for the ngram scheduling accuracy test (#62048)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
2026-10-16 18:36:14 +00:00
djramic e7a5bdb454 [ROCm][CI] Move Spec Decode Speculators + MTP to MI355 (#62053)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
2026-10-16 18:22:38 +00:00
djramic 93d0bd9d50 [ROCm][CI] Drop the -inf padding check from the AITER MQA logits test (#61420)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
2026-10-13 15:49:30 -04:00
djramic 8882b83b34 [Bugfix] Bump tokenizers to 0.23.2 for duplicate-pattern support (#59796)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
2026-10-02 18:33:50 +00:00
djramic 167a81fa9c [CI] Fix ModelExpress handling in weight transfer tests (#59772)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
2026-10-02 11:30:01 -05:00
840c7c2f4b [Bugfix][Engram] Fix intermittent Triton 3.8 crash in the lookup kernel (#59639)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
Signed-off-by: Andreas Karatzas <andreas.karatzas@protonmail.com>
Co-authored-by: Andreas Karatzas <andreas.karatzas@protonmail.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
2026-10-01 19:38:55 +00:00
djramicandAndreas Karatzas b56b54bc54 [ROCm][CI] Relax simple-nemotron-h-8b GSM8K threshold on ROCm (#59477)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
2026-09-30 19:27:21 +00:00
djramicandAndreas Karatzas 50319916a3 [ROCm][CI] Move Basic Models (Other) to MI355 (#59400)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
2026-09-30 09:42:25 +00:00
djramicandAndreas Karatzas df4dbe46e7 [CI][ROCm] Increase timeouts for AMD MI300 jobs near their limits (#59227)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
2026-09-29 18:25:49 +00:00
djramicandAndreas Karatzas 5ba2e3090b [ROCm][CI] Increase timeout for Entrypoints Unit (#59076)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
2026-09-28 17:56:10 +00:00
djramicandAndreas Karatzas 25b0add7b8 [ROCm][CI] Pass weight_shape in MXFP8 block32 linear tests (#58698)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
2026-09-25 10:52:15 +00:00
djramicandAndreas Karatzas 5fcc6e7c73 [ROCm][Bugfix] Fix TileLang mHC fused RMSNorm on 64-wide wavefronts (#58419)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
2026-09-23 23:03:45 +00:00
djramicandAndreas Karatzas 4f14516790 [ROCm][CI] Use ROCm backend for DeepSeek V4.1 ViT test (#57931)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
2026-09-21 16:39:31 +00:00
djramic 0aee727ff6 [CI][ROCm] Increase timeout for MI300 Distributed DP Extended (#57903)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
2026-09-21 04:18:59 -05:00
djramic 5392fbca2a [ROCm][Docker] Pin AINIC apt repo to snapshot 1.117.5-a-77 (#56459)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
2026-09-11 14:14:16 +00:00
djramic cce50657b7 [ROCm][CI] Use a platform-independent GEMM in the merged-column fuser test (#56130)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
2026-09-09 15:08:39 -05:00
djramicandAndreas Karatzas c6ba5e89d6 [Bugfix][Elastic EP] Route only to surviving engines during scale-down (#55772)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
2026-09-08 21:28:28 -05:00
djramic 21a117ad87 [CI][IR] Speed up vLLM IR test group (#55965)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
2026-09-08 21:28:06 -05:00
djramicandKevin H. Luu 73f61d12aa [CI][ROCm] Increase timeouts for AMD MI300 jobs (#55919)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
2026-09-08 14:06:05 -07:00
djramic 0d3ede3e3b [Bugfix][Model] Enable torch.compile for StableLM (#54969)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
2026-09-03 03:21:54 -07:00
djramic d9fbe526c0 [ROCm][CI] Skip ModernBERT FP8 MTEB test when no FP8 ScaledMM kernel exists (#53589)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
2026-08-25 08:07:09 +00:00
djramic f15ea66b30 [ROCm][Test] Use platform FP8 dtype in ModelOpt FP8_PB_WO test (#53268)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
2026-08-21 15:06:19 -05:00
djramic 5eaa70dac5 [Bugfix][Quantization] Fix INT8 W8A8 MoE crash in TritonExperts (#51411)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
2026-08-07 22:06:58 -05:00
7513d071bd [ROCm][CI] Fix XPASS(strict) on mixed audio embeds test (#49733)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
2026-07-24 16:09:18 -05:00
djramic e222c33f2f [Bugfix] Register axk1 config to fix A.X-K1 init (#49727)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
2026-07-24 12:57:49 -07:00
djramicandAndreas Karatzas b6770d7b54 [ROCm] Run init test engine in-process to avoid KV-cache OOM (#48527)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
2026-07-15 06:39:31 +00:00
djramic 49abadaedb [ROCm][Bugfix] Fix empty-tensor .max() crash in AITER FA (#47894)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
2026-07-08 16:58:36 -05:00
djramicandAndreas Karatzas f63dca6838 [ROCm] Fix encoder-decoder cross-attention KV layout aliasing (#47035)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
2026-07-03 13:53:29 -05:00
djramicandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> 61ee183d28 [ROCm] Fix AITER FP8 quantization schema tests (#46414)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-06-24 22:29:19 +08:00
djramic 0fbf42af84 [ROCm] Fix VRAM not freed in test_phi3v (#46046)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
2026-06-19 17:20:59 -05:00
djramic dec860fb19 [ROCm] Use vLLM's fp8 quant max in AITER hipBLASLt accuracy test (#46176)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
2026-06-19 13:24:02 -05:00