dongmao zhang and Michael Goin
87525fab92
[bitsandbytes]: support read bnb pre-quantized model ( #5753 )
...
Co-authored-by: Michael Goin <michael@neuralmagic.com >
2024-07-23 23:45:09 +00:00
Michael Goin
0eb0757bef
[Misc] Add ignored layers for fp8 quantization ( #6657 )
2024-07-23 14:04:04 -04:00
Michael Goin
9e0b558a09
[Misc] Support FP8 kv cache scales from compressed-tensors ( #6528 )
2024-07-23 04:11:50 +00:00
Cheng Li
c5e8330997
[Bugfix] Fix null modules_to_not_convert in FBGEMM Fp8 quantization ( #6665 )
2024-07-22 19:25:05 -07:00
Alexander Matveev
396d92d5e0
[Kernel][Core] Add AWQ support to the Marlin kernel ( #6612 )
2024-07-21 19:41:42 -04:00
Robert Shaw
082ecd80d5
[ Bugfix ] Fix AutoFP8 fp8 marlin ( #6609 )
2024-07-20 17:25:56 -06:00
Michael Goin
f952bbc8ff
[Misc] Fix input_scale typing in w8a8_utils.py ( #6579 )
2024-07-20 23:11:13 +00:00
Robert Shaw
9364f74eee
[ Kernel ] Enable fp8-marlin for fbgemm-fp8 models ( #6606 )
2024-07-20 18:50:10 +00:00
Robert Shaw
683e3cb9c4
[ Misc ] fbgemm checkpoints ( #6559 )
2024-07-20 09:36:57 -07:00
Robert Shaw
4cc24f01b1
[ Kernel ] Enable Dynamic Per Token fp8 ( #6547 )
2024-07-19 23:08:15 +00:00
Robert Shaw
dbe5588554
[ Misc ] non-uniform quantization via compressed-tensors for Llama ( #6515 )
2024-07-18 22:39:18 -04:00
Tyler Michael Smith
4ffffccb7e
[Kernel] Implement fallback for FP8 channelwise using torch._scaled_mm ( #6552 )
2024-07-18 23:52:22 +00:00
Robert Shaw
58ca663224
[ Misc ] Improve Min Capability Checking in compressed-tensors ( #6522 )
2024-07-18 14:39:12 +00:00
Robert Shaw
18fecc3559
[ Kernel ] Fp8 Channelwise Weight Support ( #6487 )
2024-07-18 03:18:13 +00:00
Michael Goin
978aed5300
[Kernel][Attention] Separate Attention.kv_scale into k_scale and v_scale ( #6081 )
2024-07-16 15:31:32 -07:00
Tyler Michael Smith
c8fd97f26d
[Kernel] Use CUTLASS kernels for the FP8 layers with Bias ( #6270 )
2024-07-15 13:05:52 -04:00
Robert Shaw
fb6af8bc08
[ Misc ] Apply MoE Refactor to Deepseekv2 To Support Fp8 ( #6417 )
2024-07-13 20:03:58 -07:00
Robert Shaw and Robert Shaw
babf52dade
[ Misc ] More Cleanup of Marlin ( #6359 )
...
Co-authored-by: Robert Shaw <rshaw@neuralmagic.com >
2024-07-13 10:21:37 +00:00
Robert Shaw
aea19f0989
[ Misc ] Support Models With Bias in compressed-tensors integration ( #6356 )
2024-07-12 11:11:29 -04:00
Robert Shaw and Robert Shaw
b675069d74
[ Misc ] Refactor Marlin Python Utilities ( #6082 )
...
Co-authored-by: Robert Shaw <rshaw@neuralmagic.com >
2024-07-11 15:40:11 +00:00
Robert Shaw and Robert Shaw
abfe705a02
[ Misc ] Support Fp8 via llm-compressor ( #6110 )
...
Co-authored-by: Robert Shaw <rshaw@neuralmagic>
2024-07-07 20:42:11 +00:00
Robert Shaw
62963d129e
[ Misc ] Clean Up CompressedTensorsW8A8 ( #6113 )
2024-07-03 22:50:08 +00:00
Michael Goin
47f0954af0
[Kernel] Expand FP8 support to Ampere GPUs using FP8 Marlin ( #5975 )
2024-07-03 17:38:00 +00:00
youkaichao
482045ee77
[hardware][misc] introduce platform abstraction ( #6080 )
2024-07-02 20:12:22 -07:00
ee93f4f92a
[CORE] Quantized lm-head Framework ( #4442 )
...
Co-authored-by: Robert Shaw <rshaw@neuralmagic.com >
Co-authored-by: ZX <zx@lbx.dev >
2024-07-02 22:25:17 +00:00
7c008c51a9
[ Misc ] Refactor MoE to isolate Fp8 From Mixtral ( #5970 )
...
Co-authored-by: Robert Shaw <rshaw@neuralmagic>
Co-authored-by: Michael Goin <michael@neuralmagic.com >
2024-07-02 21:54:35 +00:00
youkaichao
614aa51203
[misc][cuda] use nvml to avoid accidentally cuda initialization ( #6007 )
2024-06-30 20:07:34 -07:00
Robert Shaw and Robert Shaw
af9ad46fca
[ Misc ] Refactor w8a8 to use process_weights_after_load (Simplify Weight Loading) ( #5940 )
...
Co-authored-by: Robert Shaw <rshaw@neuralmagic>
2024-06-30 23:06:27 +00:00
Dipika Sikka
7836fdcc11
[Misc] Fix get_min_capability ( #5971 )
2024-06-30 20:15:16 +00:00
8dbfcd35bf
[ CI/Build ] Added E2E Test For Compressed Tensors ( #5839 )
...
Co-authored-by: Michael Goin <michael@neuralmagic.com >
Co-authored-by: Robert Shaw <rshaw@neuralmagic>
2024-06-29 21:12:58 +08:00
Robert Shaw and Robert Shaw
2cd402e169
[ Bugfix ] Enabling Loading Models With Fused QKV/MLP on Disk with FP8 ( #5921 )
...
Co-authored-by: Robert Shaw <rshaw@neuralmagic>
2024-06-28 18:43:49 +00:00
Dipika Sikka
dd248f7675
[Misc] Update w4a16 compressed-tensors support to include w8a16 ( #5794 )
2024-06-25 19:23:35 +00:00
Tyler Michael Smith
3f3b6b2150
[Bugfix] Fix the CUDA version check for FP8 support in the CUTLASS kernels ( #5715 )
2024-06-20 18:36:10 +00:00
Dipika Sikka
4a30d7e3cc
[Misc] Add per channel support for static activation quantization; update w8a8 schemes to share base classes ( #5650 )
2024-06-19 18:06:44 -04:00
Dipika Sikka
95db455e7f
[Misc] Add channel-wise quantization support for w8a8 dynamic per token activation quantization ( #5542 )
2024-06-18 12:45:05 -04:00
Dipika Sikka
890d8d960b
[Kernel] compressed-tensors marlin 24 support ( #5435 )
2024-06-17 12:32:48 -04:00
Cyrus Leung
0e9164b40a
[mypy] Enable type checking for test directory ( #5017 )
2024-06-15 04:45:31 +00:00
15985680e2
[ Misc ] Rs/compressed tensors cleanup ( #5432 )
...
Co-authored-by: mgoin <michael@neuralmagic.com >
Co-authored-by: Dipika Sikka <dipikasikka1@gmail.com >
2024-06-14 10:01:46 -07:00
Tyler Michael Smith
703475f6c2
[Kernel] Fix CUTLASS 3.x custom broadcast load epilogue ( #5516 )
2024-06-14 09:30:15 -07:00
Tyler Michael Smith
e38042d4af
[Kernel] Disable CUTLASS kernels for fp8 ( #5505 )
2024-06-13 13:38:05 -07:00
85657b5607
[Kernel] Factor out epilogues from cutlass kernels ( #5391 )
...
Co-authored-by: Michael Goin <michael@neuralmagic.com >
Co-authored-by: youkaichao <youkaichao@gmail.com >
Co-authored-by: zifeitong <zifei.tong@parasail.io >
Co-authored-by: Robert Shaw <114415538+robertgshaw2-neuralmagic@users.noreply.github.com >
2024-06-13 11:22:19 -07:00
Dipika Sikka and Robert Shaw
c2637a613b
[Kernel] w4a16 support for compressed-tensors ( #5385 )
...
Co-authored-by: Robert Shaw <114415538+robertgshaw2-neuralmagic@users.noreply.github.com >
2024-06-13 10:19:56 -04:00
Dipika Sikka and Michael Goin
5884c2b454
[Misc] Update to comply with the new compressed-tensors config ( #5350 )
...
Co-authored-by: Michael Goin <michael@neuralmagic.com >
2024-06-10 03:49:46 +00:00
Michael Goin
c09dade2a2
[Misc][Breaking] Change FP8 checkpoint format from act_scale -> input_scale ( #5353 )
2024-06-08 13:54:05 -04:00
Cheng Li
e69ded7d1c
[Bug Fix] Fix the support check for FP8 CUTLASS ( #5352 )
...
Bug description:
With torch 2.4.0.dev20240603+cu121,
cutlass_fp8_supported outputs False, and the (capability, version) before the comparison is (90, 11111111112)
This PR fixes the support check for FP8 CUTLASS ( cutlass_fp8_supported) which was introduced in https://github.com/vllm-project/vllm/pull/5183 .
2024-06-08 00:42:05 +00:00
ca3ea51bde
[Kernel] Dynamic Per-Token Activation Quantization ( #5037 )
...
Co-authored-by: Varun Sundar Rabindranath <varunsundar08@gmail.com >
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com >
2024-06-07 09:36:26 -07:00
Tyler Michael Smith
8d75fe48ca
[Kernel] Switch fp8 layers to use the CUTLASS kernels ( #5183 )
...
Switching from torch._scaled_mm to vLLM's cutlass fp8 kernels when supported as we are seeing 5-15% improvement in e2e performance on neuralmagic/Meta-Llama-3-8B-Instruct-FP8
see https://docs.google.com/spreadsheets/d/1GiAnmzyGHgZ6zL_LDSTm35Bdrt4A8AaFEurDlISYYA4/ for some quick e2e benchmarks and #5144 for comparisons across different GEMM sizes.
2024-06-07 08:42:35 +00:00
Cody Yu
5563a4dea8
[Model] Correct Mixtral FP8 checkpoint loading ( #5231 )
2024-06-05 10:58:50 -07:00
Tyler Michael Smith
cbb2f59cc8
[Kernel] Pass a device pointer into the quantize kernel for the scales ( #5159 )
2024-06-03 09:52:30 -07:00
chenqianfzh
b9c0605a8e
[Feature][Kernel] Support bitsandbytes quantization and QLoRA ( #4776 )
2024-06-01 14:51:10 -06:00
