Commit Graph
18 Commits
Author SHA1 Message Date
b2456c622b [ROCm][CI] Make ROCm 10.0 the default image; keep ROCm 7.2 as -rocm72 (#58761)
Signed-off-by: Rohan Potdar <rohan.potdar@amd.com>
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Micah Williamson <micah.williamson@amd.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
2026-10-17 21:43:59 -05:00
Rohan PotdarandClaude Opus 5.5 105605b8e9 [ROCm] Support DeepSeek-V4 hash routing in AITER Triton W4A16 MoE (#60282)
Signed-off-by: Rohan Potdar <rohan.potdar@amd.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-15 14:10:12 -05:00
Rohan PotdarandClaude Opus 5.5 9a648b4649 [ROCm][Kimi-K3] Don't read W_UK_T before weight loading in the MLA wrapper (#61654)
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-14 21:44:55 +00:00
Rohan PotdarandClaude Opus 5.5 52a8cc5316 [ROCm][CI] Add dtype to the KDA metadata test's fake model config (#61650)
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-14 18:04:14 +00:00
Rohan PotdarandClaude Opus 5.5 7900d2eabc [Test] Accept tied tokens at the k-th value in the Triton top-k test (#60726)
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-12 08:18:44 -05:00
9f1c783886 [Test] Allow one fp8 step on K bytes in the kpool decode fuzz test (#60725)
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
2026-10-10 00:26:53 +00:00
Rohan PotdarandClaude Opus 5.5 fa94ad4143 [Test] Allow one bf16 ulp in the fused mHC post/pre residual check (#60724)
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-09 17:54:06 -05:00
Rohan PotdarandClaude Opus 5.5 88a419649e [ROCm][Kimi-K3] Use vLLM's FP8 max in the fused AttnRes quantization (#60717)
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-09 04:45:13 +00:00
e440b75bb6 [ROCm] Bump torch 2.13, triton 3.8, torchaudio, torchvision (#50605)
Signed-off-by: Rohan Potdar <rohan.potdar@amd.com>
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
Signed-off-by: jpvillam <juan.villamizar@amd.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: jpvillam <juan.villamizar@amd.com>
2026-09-25 14:55:52 -05:00
3e267bae70 [ROCm] triton+triton_kernels 3.8 mxfp4 MoE support (gpt-oss + DeepSeek-V4) (#55934)
Signed-off-by: Rohan Potdar <rohan.potdar@amd.com>
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: Matt <156021403+mawong-amd@users.noreply.github.com>
2026-09-16 20:03:34 -05:00
Rohan Potdar 610bfc58e9 [ROCm] Ship rocprofiler-sdk 1.3.2 in Dockerfile.rocm_base to fix torch.profiler traces (#53182)
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
2026-08-22 12:16:25 -05:00
Rohan Potdar 823ec22b78 [ROCm]: Bump triton 3.7 commit (#52819)
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
2026-08-19 17:39:08 -05:00
Rohan Potdar 9df9b0b0a1 [ROCm]: Drop pybind11 from Dockerfile.rocm to prevent version mismatch (#52400)
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
2026-08-14 23:50:23 +00:00
Rohan PotdarandClaude Opus 4.8 38ebd97bca [ROCm] Relax MLA rope+cache test tolerances for bf16 (#51083)
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-08-05 17:50:52 -05:00
Rohan PotdarandClaude Opus 4.8 c2d8009044 [ROCm] Work around DeepEP teardown SIGSEGV in MoE test harness (#51174)
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-08-05 14:44:42 -05:00
Rohan PotdarandClaude Opus 4.8 d0ce3dadb6 [ROCm]: Bump torch 2.12, triton 3.7, torchaudio, torchvision (#50607)
Signed-off-by: Rohan Potdar <rohan.potdar@amd.com>
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-08-04 20:14:11 -05:00
Rohan PotdarandClaude Opus 4.8 2ff76a5e85 [ROCm][Bugfix] Pass num_kv_splits to aiter mla_reduce_v1 (#46760)
Signed-off-by: Rohan Potdar <rohanpotdar138@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-26 21:58:40 +00:00
Rohan Potdar e53a17232c [ROCm]: Bump aiter to 0.1.16.post2 (#46692)
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
2026-06-25 11:53:26 -07:00