192 Commits

Author SHA1 Message Date
Dipika Sikka
b866cdbd05
[Misc] Add assertion and helpful message for marlin24 compressed models (#11388) 2024-12-24 02:23:38 +08:00
George
51ff216d85
[Bugfix] update should_ignore_layer (#11354)
Signed-off-by: George Ohashi <george@neuralmagic.com>
2024-12-21 06:36:23 +00:00
Isotr0py
276738ce0f
[Bugfix] Fix broken CPU compressed-tensors test (#11338)
Signed-off-by: Isotr0py <2037008807@qq.com>
2024-12-19 17:37:31 +00:00
Tyler Michael Smith
5a9da2e6e9
[Bugfix][Build/CI] Fix sparse CUTLASS compilation on CUDA [12.0, 12.2) (#11311)
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
2024-12-19 02:43:30 +00:00
Dipika Sikka
60508ffda9
[Kernel]: Cutlass 2:4 Sparsity + FP8/Int8 Quant Support (#10995)
Co-authored-by: Faraz Shahsavan <faraz.shahsavan@gmail.com>
Co-authored-by: ilmarkov <markovilya197@gmail.com>
Co-authored-by: Rahul Tuli <rahul@neuralmagic.com>
Co-authored-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
2024-12-18 09:57:16 -05:00
Jee Jee Li
15859f2357
[[Misc]Upgrade bitsandbytes to the latest version 0.45.0 (#11201) 2024-12-15 03:03:06 +00:00
Isotr0py
b98c62ba49
[Bugfix] Fix GGUF inference with FP16 unquantized checkpoint (#10675)
Signed-off-by: Isotr0py <2037008807@qq.com>
2024-11-27 10:43:17 -08:00
yansh97
cfb3bf25fb
[bugfix] fix the default value of llm_int8_threshold in BitsAndBytesConfig (#10657) 2024-11-27 13:55:23 +08:00
Michael Goin
7576cd38df
[Bugfix] Check bnb_4bit_quant_storage for bitsandbytes (#10642) 2024-11-26 12:29:00 -08:00
youkaichao
388ee3de66
[torch.compile] limit inductor threads and lazy import quant (#10482)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-20 18:36:33 -08:00
ElizaWszola
b00b33d77e
[Model][Quantization] HQQ support through Marlin kernel expansion (#9766)
Signed-off-by: ElizaWszola <eliza@neuralmagic.com>
2024-11-19 13:31:12 -08:00
Lucas Wilkinson
96d999fbe8
[Kernel] Initial Machete W4A8 support + Refactors (#9855)
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
2024-11-18 12:59:29 -07:00
Angus Wang
c2170a5b39
[Kernel] Explicitly specify other value in tl.load calls (#9014)
Signed-off-by: Angus Wang <wangjadehao@gmail.com>
2024-11-18 11:39:40 -08:00
Yan Ma
6b2d25efc7
[Hardware][XPU] AWQ/GPTQ support for xpu backend (#10107)
Signed-off-by: yan ma <yan.ma@intel.com>
2024-11-18 11:18:05 -07:00
Luka Govedič
bf2ddc6610
[bugfix] Fix static asymmetric quantization case (#10334)
Signed-off-by: Daniël de Kok <me@danieldk.eu>
Signed-off-by: luka <luka@neuralmagic.com>
Co-authored-by: Daniël de Kok <me@danieldk.eu>
2024-11-15 09:35:11 +08:00
rasmith
127c07480e
[Kernel][Triton] Add Triton implementation for scaled_mm_triton to support fp8 and int8 SmoothQuant, symmetric case (#9857)
Signed-off-by: Randall Smith <Randall.Smith@amd.com>
2024-11-08 19:59:22 -05:00
Li, Jiang
a4b3e0c1e9
[Hardware][CPU] Update torch 2.5 (#9911)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
2024-11-07 04:43:08 +00:00
Michael Goin
4ab3256644
[Bugfix] Fix FP8 torch._scaled_mm fallback for torch>2.5 with CUDA<12.4 (#10095)
Signed-off-by: mgoin <michael@neuralmagic.com>
2024-11-07 00:54:13 +00:00
Michael Goin
399c798608
Remove ScaledActivation for AWQ (#10057)
Signed-off-by: mgoin <michael@neuralmagic.com>
2024-11-06 14:27:06 +00:00
Jee Jee Li
b9c64c0ca7
[Misc] Modify BNB parameter name (#9997)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2024-11-05 14:40:08 -05:00
Michael Goin
8f0a9ca890
[Bugfix] Respect modules_to_not_convert within awq_marlin (#9895)
Signed-off-by: mgoin <michael@neuralmagic.com>
2024-11-04 16:57:44 -07:00
Pavani Majety
598b6d7b07
[Bugfix/Core] Flashinfer k_scale and v_scale (#9861) 2024-11-01 12:15:05 -07:00
Michael Goin
37a4947dcd
[Bugfix] Fix layer skip logic with bitsandbytes (#9887)
Signed-off-by: mgoin <michael@neuralmagic.com>
2024-11-01 13:12:44 +08:00
Michael Goin
226688bd61
[Bugfix][VLM] Make apply_fp8_linear work with >2D input (#9812) 2024-10-29 19:49:44 -07:00
Isotr0py
09500f7dde
[Model] Add BNB quantization support for Mllama (#9720) 2024-10-29 08:20:02 -04:00
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
Michael Goin
ca0d92227e
[Bugfix] Fix compressed_tensors_moe bad config.strategy (#9677) 2024-10-25 12:40:33 -07:00
Cyrus Leung
c18e1a3418
[VLM] Enable overriding whether post layernorm is used in vision encoder + fix quant args (#9217)
Co-authored-by: Isotr0py <2037008807@qq.com>
2024-10-23 11:27:37 +00:00
Dipika Sikka
48138a8415
[BugFix] Stop silent failures on compressed-tensors parsing (#9381) 2024-10-17 18:54:00 -07:00
Lucas Wilkinson
e312e52b44
[Kernel] Add Exllama as a backend for compressed-tensors (#9395) 2024-10-17 09:48:26 -04:00
Michael Goin
22f8a69549
[Misc] Directly use compressed-tensors for checkpoint definitions (#8909)
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-10-15 15:40:25 -07:00
Li, Jiang
ca77dd7a44
[Hardware][CPU] Support AWQ for CPU backend (#7515) 2024-10-09 10:28:08 -06:00
chenqianfzh
2f4117c38e
support bitsandbytes quantization with more models (#9148) 2024-10-08 19:52:19 -06:00
Isotr0py
f19da64871
[Core] Refactor GGUF parameters packing and forwarding (#8859) 2024-10-07 10:01:46 +00:00
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
Cyrus Leung
e1a3f5e831
[CI/Build] Update models tests & examples (#8874)
Co-authored-by: Roger Wang <ywang@roblox.com>
2024-09-28 09:54:35 -07:00
Lucas Wilkinson
c5d55356f9
[Bugfix] fix for deepseek w4a16 (#8906)
Co-authored-by: mgoin <michael@neuralmagic.com>
2024-09-27 13:12:34 -06:00
Luka Govedič
172d1cd276
[Kernel] AQ AZP 4/4: Integrate asymmetric quantization to linear method (#7271) 2024-09-27 14:25:10 -04:00
Michael Goin
873edda6cf
[Misc] Support FP8 MoE for compressed-tensors (#8588) 2024-09-25 09:43:36 -07:00
bnellnm
300da09177
[Kernel] Fullgraph and opcheck tests (#8479) 2024-09-25 08:35:52 -06:00
Jee Jee Li
13f9f7a3d0
[[Misc]Upgrade bitsandbytes to the latest version 0.44.0 (#8768) 2024-09-24 17:08:55 -07:00
Lucas Wilkinson
72fc97a0f1
[Bugfix] Fix torch dynamo fixes caused by replace_parameters (#8748) 2024-09-24 14:33:21 -04:00
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
rasmith
ec4aaad812
[Kernel][Triton][AMD] Remove tl.atomic_add from awq_gemm_kernel, 2-5x speedup MI300, minor improvement for MI250 (#8646) 2024-09-21 09:20:54 +00:00
Gregory Shtrasberg
b3195bc9e4
[AMD][ROCm]Quantization methods on ROCm; Fix _scaled_mm call (#8380)
Co-authored-by: Alexei-V-Ivanov-AMD <156011006+Alexei-V-Ivanov-AMD@users.noreply.github.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>
2024-09-18 10:41:08 -07:00
Aaron Pham
9d104b5beb
[CI/Build] Update Ruff version (#8469)
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2024-09-18 11:00:56 +00:00
Cyrus Leung
6ffa3f314c
[CI/Build] Avoid CUDA initialization (#8534) 2024-09-18 10:38:11 +00:00
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