585 Commits

Author SHA1 Message Date
Aaron Pham
21063c11c7
[CI/Build] drop support for Python 3.8 EOL (#8464)
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
2024-11-06 07:11:55 +00:00
Michael Goin
235366fe2e
[CI] Prune back the number of tests in tests/kernels/* (#9932)
Signed-off-by: mgoin <michael@neuralmagic.com>
2024-11-05 16:02:32 -05:00
sroy745
a78dd3303e
[Encoder Decoder] Add flash_attn kernel support for encoder-decoder models (#9559) 2024-11-01 23:22:49 -07:00
Peter Salas
6c0b7f548d
[Core][VLM] Add precise multi-modal placeholder tracking (#8346)
Signed-off-by: Peter Salas <peter@fixie.ai>
2024-11-01 16:21:10 -07:00
Pavani Majety
598b6d7b07
[Bugfix/Core] Flashinfer k_scale and v_scale (#9861) 2024-11-01 12:15:05 -07:00
Mor Zusman
9fb12f7848
[BugFix][Kernel] Fix Illegal memory access in causal_conv1d in H100 (#9838)
Signed-off-by: mzusman <mor.zusmann@gmail.com>
2024-10-31 20:06:25 +00:00
wangshuai09
622b7ab955
[Hardware] using current_platform.seed_everything (#9785)
Signed-off-by: wangshuai09 <391746016@qq.com>
2024-10-29 14:47:44 +00:00
youkaichao
32176fee73
[torch.compile] support moe models (#9632)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-10-27 21:58:04 -07:00
wangshuai09
4e2d95e372
[Hardware][ROCM] using current_platform.is_rocm (#9642)
Signed-off-by: wangshuai09 <391746016@qq.com>
2024-10-28 04:07:00 +00:00
Mengqing Cao
5cbdccd151
[Hardware][openvino] is_openvino --> current_platform.is_openvino (#9716) 2024-10-26 10:59:06 +00:00
Charlie Fu
59449095ab
[Performance][Kernel] Fused_moe Performance Improvement (#9384)
Signed-off-by: charlifu <charlifu@amd.com>
2024-10-24 15:37:52 -07:00
Jee Jee Li
295a061fb3
[Kernel] add kernel for FATReLU (#9610)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2024-10-24 16:18:27 +08:00
wangshuai09
3ddbe25502
[Hardware][CPU] using current_platform.is_cpu (#9536) 2024-10-22 00:50:43 -07:00
Chen Zhang
4fa3e33349
[Kernel] Support sliding window in flash attention backend (#9403) 2024-10-20 10:57:52 -07:00
bnellnm
eca2c5f7c0
[Bugfix] Fix support for dimension like integers and ScalarType (#9299) 2024-10-17 19:08:34 +00:00
Mor Zusman
fb60ae9b91
[Kernel][Model] Improve continuous batching for Jamba and Mamba (#9189) 2024-10-16 12:12:43 -04:00
Cyrus Leung
7e7eae338d
[Misc] Standardize RoPE handling for Qwen2-VL (#9250) 2024-10-16 13:56:17 +08:00
Tyler Michael Smith
7342a7d7f8
[Model] Support Mamba (#6484) 2024-10-11 15:40:06 +00:00
Lucas Wilkinson
a64e7b9407
[Bugfix] Machete garbage results for some models (large K dim) (#9212) 2024-10-10 14:16:17 +08:00
bnellnm
bd37b9fbe2
[Bugfix] Try to handle older versions of pytorch (#9086) 2024-10-08 14:28:12 -07:00
ElizaWszola
05d686432f
[Kernel] Zero point support in fused MarlinMoE kernel + AWQ Fused MoE (#8973)
Co-authored-by: Dipika <dipikasikka1@gmail.com>
Co-authored-by: Dipika Sikka <ds3822@columbia.edu>
2024-10-04 12:34:44 -06:00
youkaichao
9aaf14c62e
[misc] add forward context for attention (#9029) 2024-10-03 12:09:42 -07:00
Mor Zusman
f13a07b1f8
[Kernel][Model] Varlen prefill + Prefill chunking support for mamba kernels and Jamba model (#8533) 2024-09-29 17:35:58 -04:00
ElizaWszola
d081da0064
[Bugfix] Fix Marlin MoE act order when is_k_full == False (#8741)
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
2024-09-28 18:19:40 -07:00
youkaichao
a9b15c606f
[torch.compile] use empty tensor instead of None for profiling (#8875) 2024-09-27 08:11:32 -07:00
bnellnm
300da09177
[Kernel] Fullgraph and opcheck tests (#8479) 2024-09-25 08:35:52 -06:00
Lucas Wilkinson
86e9c8df29
[Kernel] (2/N) Machete - Integrate into CompressedTensorsWNA16 and GPTQMarlin (#7701)
Co-authored-by: mgoin <michael@neuralmagic.com>
Co-authored-by: Divakar Verma <137818590+divakar-amd@users.noreply.github.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
2024-09-23 13:46:26 -04:00
Charlie Fu
9cc373f390
[Kernel][Amd] Add fp8 kv cache support for rocm custom paged attention (#8577) 2024-09-19 17:37:57 +00:00
Tyler Michael Smith
db9120cded
[Kernel] Change interface to Mamba selective_state_update for continuous batching (#8039) 2024-09-18 20:05:06 +00:00
Cyrus Leung
6ffa3f314c
[CI/Build] Avoid CUDA initialization (#8534) 2024-09-18 10:38:11 +00:00
Tyler Michael Smith
8110e44529
[Kernel] Change interface to Mamba causal_conv1d_update for continuous batching (#8012) 2024-09-17 23:44:27 +00:00
Simon Mo
546034b466
[refactor] remove triton based sampler (#8524) 2024-09-16 20:04:48 -07:00
Luka Govedič
5d73ae49d6
[Kernel] AQ AZP 3/4: Asymmetric quantization kernels (#7270) 2024-09-16 11:52:40 -07:00
ElizaWszola
a091e2da3e
[Kernel] Enable 8-bit weights in Fused Marlin MoE (#8032)
Co-authored-by: Dipika <dipikasikka1@gmail.com>
2024-09-16 09:47:19 -06:00
Isotr0py
fc990f9795
[Bugfix][Kernel] Add IQ1_M quantization implementation to GGUF kernel (#8357) 2024-09-15 16:51:44 -06:00
Charlie Fu
1ef0d2efd0
[Kernel][Hardware][Amd]Custom paged attention kernel for rocm (#8310) 2024-09-13 17:01:11 -07:00
Cyrus Leung
a84e598e21
[CI/Build] Reorganize models tests (#7820) 2024-09-13 10:20:06 -07:00
bnellnm
73202dbe77
[Kernel][Misc] register ops to prevent graph breaks (#6917)
Co-authored-by: Sage Moore <sage@neuralmagic.com>
2024-09-11 12:52:19 -07:00
Dipika Sikka
6cd5e5b07e
[Misc] Fused MoE Marlin support for GPTQ (#8217) 2024-09-09 23:02:52 -04:00
Elfie Guo
e39ebf5cf5
[Core/Bugfix] Add query dtype as per FlashInfer API requirements. (#8173) 2024-09-05 05:12:26 +00:00
Pavani Majety
6b3421567d
[Core][Kernels] Enable FP8 KV Cache with Flashinfer backend. + BugFix for kv_cache_dtype=auto (#7985)
Co-authored-by: Simon Mo <simon.mo@hey.com>
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>
2024-08-29 14:53:11 -04:00
youkaichao
ef99a78760
Revert "[Core][Kernels] Use FlashInfer backend for FP8 KV Cache when available." (#7982) 2024-08-28 21:27:06 -07:00
Mor Zusman
fdd9daafa3
[Kernel/Model] Migrate mamba_ssm and causal_conv1d kernels to vLLM (#7651) 2024-08-28 15:06:52 -07:00
rasmith
e5697d161c
[Kernel] [Triton] [AMD] Adding Triton implementations awq_dequantize and awq_gemm to support AWQ (#7386) 2024-08-28 15:37:47 -04:00
Pavani Majety
b98cc28f91
[Core][Kernels] Use FlashInfer backend for FP8 KV Cache when available. (#7798)
Co-authored-by: Simon Mo <simon.mo@hey.com>
2024-08-28 10:01:22 -07:00
LI MOU
53328d7536
[BUG] fix crash on flashinfer backend with cudagraph disabled, when attention group_size not in [1,2,4,8] (#7509) 2024-08-21 08:54:31 -07:00
Lucas Wilkinson
5288c06aa0
[Kernel] (1/N) Machete - Hopper Optimized Mixed Precision Linear Kernel (#7174) 2024-08-20 07:09:33 -06:00
Charlie Fu
e837b624f2
[Feature][Hardware][Amd] Add fp8 Linear Layer for Rocm (#7210) 2024-08-16 10:06:30 -07:00
youkaichao
54bd9a03c4
register custom op for flash attn and use from torch.ops (#7536) 2024-08-15 22:38:56 -07:00
jon-chuang
50b8d08dbd
[Misc/Testing] Use torch.testing.assert_close (#7324) 2024-08-16 04:24:04 +00:00