 Divakar VermaandClaude Sonnet 5
|
f7ba007b5e
|
[ROCm][MoE] Split AiterExperts by weight-quantization key (#60322)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
|
2026-10-13 00:13:33 -05:00 |
|
|
Divakar Verma
|
c5c1161382
|
[ROCm][Build] Fail fast when setup.py develop deps aren't pip-preinstalled (#59447)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-10-08 15:28:38 -05:00 |
|
|
Divakar VermaandAndreas Karatzas
|
18751bc6a7
|
[ROCm][CI] Add coverage for AiterExperts token padding: inf/nan garbage rows (#59334)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-10-08 19:11:45 +00:00 |
|
|
Divakar VermaandAndreas Karatzas
|
efb8d85f24
|
[ROCm][CI] Add FP32 rounding slack to accuracy test near-tie upper bounds (#60292)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-10-07 08:19:22 -05:00 |
|
|
Divakar Verma
|
faa9860dbd
|
[ROCm][CI][AiterExperts] Add test coverage for hidden/intermediate padding correctness (#59333)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-10-03 01:53:37 +00:00 |
|
|
Divakar Verma
|
6abadc2aa7
|
[ROCm][CI] Add test coverage for VLLM_ROCM_MOE_PADDING memory-stride padding transparency (#59332)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-10-02 11:23:22 -05:00 |
|
|
Divakar Verma
|
2a537887de
|
[CI] Use vllm_runner in fusions_e2e conftest for reliable GPU cleanup (#59525)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-10-02 11:21:21 -05:00 |
|
|
Divakar VermaandClaude Sonnet 5
|
e6674262f1
|
[Bugfix][CI] Widen DBO+DP+EP GSM8K accuracy margin on ROCm (#59700)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
|
2026-10-01 23:37:36 +00:00 |
|
|
Divakar Verma
|
65c5e24689
|
[ROCm][CI][AITER Coverage] Harden MoE sorting-backend/dispatch env-var test matrix (#58393)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-09-24 21:14:02 -05:00 |
|
|
Divakar VermaandAndreas Karatzas
|
d1f63f2af9
|
[ROCm][CI] Add GELU activation for AiterExperts in the modular-kernel coverage (#58030)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-09-22 14:39:13 -05:00 |
|
|
Divakar VermaandAndreas Karatzas
|
95f4925c3a
|
[ROCm][CI] Enable AITER FP8/unquantized cases in modular-kernel sweep + fix MoRI per-tensor FP8 dispatch (#57074)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-09-16 19:53:06 -05:00 |
|
|
Divakar Verma
|
06e57f622c
|
[ROCm][Kimi-K3] Fix non-contiguous state_indices crash and GPU-sync assert in fused KDA/MLA prefill (#56526)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-09-11 20:17:39 -05:00 |
|
|
Divakar VermaandAndreas Karatzas
|
3fb676bfad
|
[ROCm][CI] Fix moe layer tests for fp8 dtype compatibility (#56106)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-09-09 17:48:14 +00:00 |
|
|
Divakar VermaandAndreas Karatzas
|
dbf1a044ea
|
[Bugfix] Fix ColQwen3.5 pooler projector initialization (#54847)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-09-02 10:35:43 +08:00 |
|
|
Divakar VermaandAndreas Karatzas
|
c0adee9231
|
[ROCm][CI] Add ROCm misc ops and env tests (#53279)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-09-01 19:03:37 +00:00 |
|
|
Divakar Verma
|
29b7c2f7d4
|
[ROCm][CI] aiter kernel ops - enable rope test (#52854)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-08-21 15:17:34 -05:00 |
|
|
Divakar Verma
|
b5f7fcc79d
|
[ROCm][CI] Add float16 dtype and unsupported head size tests for paged attention (#53177)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-08-21 15:16:45 -05:00 |
|
|
Divakar Verma
|
49fb2ee348
|
[ROCm][CI] add Aiter ops tests (#52208)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-08-17 18:33:22 -05:00 |
|
|
Divakar Verma
|
4f851bef6c
|
[ROCm][CI] Update AITER AR+RMS e2e fusion counts for final-norm coverage (#51273)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-08-06 13:05:16 -05:00 |
|
|
Divakar Verma
|
bb543efdfd
|
[ROCm][CI] Add aiter per-token FP8 quant roundtrip and RMSNorm determinism tests (#50905)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-08-04 21:32:08 -05:00 |
|
|
Divakar Verma
|
fe65aa6a97
|
[CI][NIXL] Fix flaky DP+EP test port conflict (#50171)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-07-29 00:12:50 +00:00 |
|
|
Divakar Verma
|
aaaeda98dc
|
[CI] fix compile test | refactor VLLM_DISABLE_COMPILE_CACHE for tests (#49770)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-07-24 23:15:19 -05:00 |
|
|
Divakar Verma
|
53c2f20dd9
|
[ROCm][CI] skip moe weight padding for eplb (#49350)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-07-22 10:18:01 -05:00 |
|
|
Divakar Verma
|
05d4f8bba3
|
[ROCm][CI] fix flashinfer import check (#48647)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-07-14 20:54:19 +00:00 |
|
|
Divakar Verma
|
68ee8300a0
|
[ROCm][CI]Fix test_concat_and_cache_mla_rope_fused on ROCm (#46409)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-06-27 12:38:13 +08:00 |
|
|
Divakar Verma
|
00e045b7c7
|
[ROCm][CI TG] refactor and fix deepep_moe test group (#46758)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-06-27 10:45:23 +08:00 |
|
|
Divakar Verma
|
17a71d8702
|
[ROCm][CI] Relax fused layernorm quant test tolerances for one-ULP outliers (#46658)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-06-27 10:44:29 +08:00 |
|
|
Divakar Verma
|
cdfa2fd7e9
|
[ROCm][CI] rm duplicate Distributed Torchrun ci test (#46729)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-06-25 09:58:17 -05:00 |
|
|
|
84586c9acc
|
[ROCm][CI] fix fp8 range in vit_fp8_quant (#46410)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Signed-off-by: Divakar Verma <137818590+divakar-amd@users.noreply.github.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2026-06-23 11:34:21 -05:00 |
|
|
Divakar VermaandAndreas Karatzas
|
568874fec2
|
[ROCm][CI] pass merge-base to container for python-only wheel metadata (#45869)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-06-23 15:44:43 +00:00 |
|
|
Divakar Verma
|
21da47dabe
|
[ROCm][CI] move lora%N test to mi300 and gate (#45970)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-06-19 00:50:32 +08:00 |
|
|
Divakar Verma
|
4fadf9c92c
|
[ROCm][CI] fix multimodel run cmds (#45858)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-06-16 15:31:52 -05:00 |
|
|
Divakar Verma
|
1ce3cdc5c1
|
[ROCm][CI] fix fp8 support for test_deepep_moe (#45302)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-06-12 00:16:14 -05:00 |
|
|
Divakar Verma
|
166d14e9bf
|
[bugfix] skip conch kernel for g_idx reordering (#45072)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-06-10 23:04:19 +08:00 |
|
|
Divakar VermaandAndreas Karatzas
|
06f94633e7
|
[ROCm][CI] Add test for Aiter unified attn kernel (#44436)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-06-04 16:15:05 +00:00 |
|
|
Divakar Verma
|
35d0141a0b
|
[ROCm][CI] add warmup to mem_util test before measurement (#43236)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-05-22 03:17:54 +00:00 |
|
|
Divakar Verma
|
ca7e4546da
|
[CI] set max transformers version for skywork model (#42104)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-05-13 16:53:49 -07:00 |
|
|
Divakar Verma
|
22a3cbe152
|
[ROCm] aiter_unified_attn fp8 q scale refactor (#38296)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-05-06 16:11:36 +00:00 |
|
|
Divakar Verma
|
b9dbc5c4ab
|
[Mamba][APC] Add test case to compare apc outputs (#34977)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-03-26 16:40:35 +00:00 |
|
|
Divakar Verma
|
4ca3fa6bb4
|
[ROCm][Bugfix] fix cache block size mismatch for aiter unified attention (#37606)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-03-20 00:00:08 +00:00 |
|
|
Divakar Verma
|
e6c4797704
|
[ROCm][Quantization] add fp8xfp8 attn support for rocm_aiter_unified_attn (#36927)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-03-18 08:49:32 +08:00 |
|
|
Divakar Verma
|
6341d43043
|
[ROCm][Quantization] add quark w4a8 mxfp4_fp8 for LinearLayer (#35316)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-03-13 19:44:24 +00:00 |
|
|
Divakar Verma
|
49d9653852
|
[ROCm][CI] fix get_valid_backends (#32787)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-01-22 04:27:47 +00:00 |
|
|
Divakar Verma
|
180fba653e
|
[ROCm] fix import for on_gfx9 (#32783)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-01-21 18:41:11 +00:00 |
|
|
Divakar Verma
|
e14467be43
|
[bugfix] Aria model (#32727)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-01-21 05:11:31 -08:00 |
|
|
Divakar Verma
|
a28d9f4470
|
[ROCm][CI] Handle pytest status code 5 when a shard isn't allocated any tests (#32040)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-01-12 17:35:49 -05:00 |
|
|
Divakar Verma
|
a1648c4045
|
[ROCm][CI] Fix test_token_classification.py::test_bert_models (#31993)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-01-09 04:04:33 +00:00 |
|
|
Divakar Verma
|
78e5e62bbf
|
[AMD][CI] fix v1/engine test_preprocess_error_handling (#31192)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2025-12-23 01:28:19 +00:00 |
|
|
Divakar Verma
|
82dc338ad6
|
[AMD][CI] fix lm eval ci arg (#30911)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2025-12-18 13:18:26 +08:00 |
|
|
|
d1e1fb4363
|
[Bugfix] Fix grouped_topk pytorch impl when num_experts can't be grouped properly (#29439)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Co-authored-by: Gregory Shtrasberg <156009573+gshtras@users.noreply.github.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
|
2025-12-10 19:47:18 -08:00 |
|
|
Divakar Verma
|
962d703818
|
[Bugfix][llama4_eagle] Fix missing 'lm_head' attribute (#29926)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2025-12-05 19:57:26 +00:00 |
|
|
Divakar Verma
|
afb1e5b380
|
[CI][ROCm][tests/v1/e2e] Fix multiprocessing launch for the test (#29123)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2025-12-02 20:46:10 +00:00 |
|
|
Divakar Verma
|
e2fbfc955e
|
[CI][AMD] spec_decode:eagle skip FLASH_ATTN for deepseek on ROCm (#29827)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2025-12-02 05:27:46 +00:00 |
|
|
Divakar VermaandCyrus Leung
|
a690fb5bd6
|
[CI][ROCm] Fix test_correctness_sliding_window (#29243)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2025-12-02 04:53:27 +00:00 |
|
|
Divakar Vermaandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
4b40924998
|
[ROCm] Fallback pytorch GELU with tanh approximation to GELU() (#29244)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Signed-off-by: Divakar Verma <137818590+divakar-amd@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
2025-12-02 02:02:22 +00:00 |
|
|
Divakar Verma
|
22b42b5402
|
[CI][ROCm] Install arctic-inference on ROCm tests (#29344)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2025-11-25 02:15:39 +00:00 |
|
|
Divakar VermaandShaoChunLee
|
04d1dd7f4a
|
[ROCm][Aiter] Add triton fp8 bmm kernel for mla (#23264)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Co-authored-by: ShaoChunLee <Shao-Chun.Lee@amd.com>
|
2025-08-28 18:18:08 +00:00 |
|
|
Divakar Verma
|
774c5fde30
|
[V1] fix torch profiling for V1 offline scenarios (#18445)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2025-05-28 04:16:30 +00:00 |
|
|
Divakar Verma
|
1d4680fad2
|
[rocm][MI300] llama4 maverick fp8 moe config tp8 (#16847)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2025-04-19 06:21:43 +00:00 |
|
|
Divakar Verma
|
95aca283b4
|
[rocm][V0] fix selection logic for custom PA in V0 (#16426)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2025-04-16 19:52:11 -07:00 |
|
|
Divakar Verma
|
bb5b640359
|
[core] moe fp8 block quant tuning support (#14068)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2025-03-04 01:30:23 +00:00 |
|
|
Divakar Verma
|
0d243f2a54
|
[ROCm][MoE] mi300 mixtral8x7B perf for specific BS (#13577)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2025-02-20 04:01:02 +00:00 |
|
|
Divakar Verma
|
8aada19dfc
|
[ROCm][MoE configs] mi325 mixtral & mi300 qwen_moe (#13503)
|
2025-02-18 22:23:24 -08:00 |
|
|
Divakar Verma
|
7c7adf81fc
|
[ROCm] fix get_device_name for rocm (#13438)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2025-02-18 04:07:12 +00:00 |
|
|
Divakar Verma
|
1c1bb0bbf2
|
[Misc][MoE] add Deepseek-V3 moe tuning support (#12558)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2025-01-30 00:47:30 +00:00 |
|
|
Divakar Verma
|
bf21481dde
|
[ROCm][MoE] MI300 tuned configs Mixtral-8x(7B,22B) | fp16, fp8 (#12408)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2025-01-25 12:17:19 +08:00 |
|
|
Divakar Verma
|
2acba47d9b
|
[bugfix] moe tuning. rm is_navi() (#12273)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2025-01-21 22:47:32 +00:00 |
|
|
Divakar Verma
|
8027a72461
|
[ROCm][MoE] moe tuning support for rocm (#12049)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2025-01-17 14:49:16 +08:00 |
|
|
Divakar Verma
|
4d29e91be8
|
[Misc] sort torch profiler table by kernel timing (#11813)
|
2025-01-08 10:57:04 +08:00 |
|
|
Divakar Verma
|
01843c89b8
|
[Misc] log when using default MoE config (#8971)
|
2024-10-03 04:31:07 +00:00 |
|
|
Divakar Verma
|
82f3937e59
|
[Misc] add process_weights_after_loading for DummyLoader (#8969)
|
2024-10-01 03:46:41 +00:00 |
|
|
Divakar Verma
|
9dc7c6c7f3
|
[dbrx] refactor dbrx experts to extend FusedMoe class (#8518)
|
2024-09-21 15:09:39 -06:00 |
|
|
Divakar Verma
|
c3dde367f1
|
[Kernel][ROCm][AMD] fused_moe Triton configs v2 for mi300X (#5932)
|
2024-06-27 13:41:08 -07:00 |
|
|
Divakar Verma
|
a66cf40b20
|
[Kernel][ROCm][AMD] enable fused topk_softmax kernel for moe layer (#4927)
This PR enables the fused topk_softmax kernel used in moe layer for HIP
|
2024-06-02 14:13:26 -07:00 |
|
|
Divakar Verma
|
dd8de11f0a
|
[Kernel][ROCm][AMD] Add fused_moe Triton configs for MI300X (#4951)
This PR adds Triton kernel configs for the MoE kernel for MI300X
|
2024-05-28 16:03:23 +00:00 |
|