issues
search
neuralmagic
/
sparseml
Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models
Apache License 2.0
2.07k
stars
148
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
FP8 Quantization Support
#2306
Satrat
closed
5 months ago
0
[Fix] Fully functional FSDP one-shot process
#2305
dbogunowicz
closed
5 months ago
0
[GHA] Update End-to-End Nightly Build Process
#2304
dsikka
closed
5 months ago
0
Example/ux
#2303
horheynm
closed
5 months ago
0
Fixing Multi-GPU Unit Test Issue
#2302
Satrat
closed
5 months ago
0
Update Examples to New UX
#2301
Satrat
closed
5 months ago
1
Fix transformers tests
#2300
rahul-tuli
closed
6 months ago
0
Fix errors introduced by GPTQ UX
#2299
rahul-tuli
closed
6 months ago
1
fix
#2298
horheynm
closed
6 months ago
0
Fix Platypus template when there are no inputs (additional one)
#2297
eldarkurtic
closed
6 months ago
0
Fix Platypus template when there are no inputs
#2296
eldarkurtic
closed
6 months ago
0
Bump requests from 2.31.0 to 2.32.0 in /research/information_retrieval/doc2query
#2295
dependabot[bot]
opened
6 months ago
0
[GPTQ Modifier UX] Update tests to use GPTQModifier for obcq style quantization
#2294
rahul-tuli
closed
6 months ago
0
How to export a GPTQ model to ONNX to run in DeepSparse
#2293
Tangxinlu
opened
6 months ago
2
Fixes for sparseml.evaluate
#2292
Satrat
closed
6 months ago
0
[Cherry-Pick] Make reloading compatible with safetensors
#2291
dbogunowicz
closed
6 months ago
0
[GTPQ] fix slice of scale/zp for group_size
#2290
bfineran
closed
6 months ago
0
Support for compressed-tensors-nightly
#2289
dbogunowicz
closed
6 months ago
0
[1.7] Enable one-shot flow for non-LLMs
#2288
dbogunowicz
closed
6 months ago
0
[GPTQ UX] Add string aliasing support for scheme
#2287
rahul-tuli
closed
6 months ago
0
[GPTQ UX] Add scheme arg with QuantizationScheme support
#2286
rahul-tuli
closed
6 months ago
0
Llama2 7B Quantization Examples
#2285
Satrat
closed
6 months ago
1
mask_structure preservation test
#2284
rahul-tuli
closed
6 months ago
0
Channelwise Quantization Tests
#2283
Satrat
closed
5 months ago
1
Preserve sparsity SPARSEGPT
#2282
rahul-tuli
closed
6 months ago
0
Preserve sparsity GPTQ
#2281
rahul-tuli
closed
6 months ago
0
fix group size support for sgpt_wrapper
#2280
bfineran
closed
6 months ago
0
update
#2279
dsikka
closed
6 months ago
0
test
#2278
rahul-tuli
closed
6 months ago
1
[GHA] Swap aws runners; remove internal pypi step
#2277
dsikka
closed
6 months ago
0
Performance Degradation in YOLOv8s Model Exported to ONNX via SparseML's Exporter
#2276
rsazizov
opened
6 months ago
10
[Prototyping] Roberta Demo
#2275
dbogunowicz
closed
6 months ago
1
[Testing] Update/expand finetune tests
#2274
dsikka
closed
6 months ago
0
GPTQ UX config groups support
#2273
rahul-tuli
closed
6 months ago
2
Split SparseGPT and GPTQ modifiers
#2272
rahul-tuli
closed
6 months ago
1
[GHA] Add workflow files to run weekly and nightly tests/run oneshot and finetune llama-7b model tests
#2271
dsikka
closed
6 months ago
0
[GHA] Add steps to publish nightly wheel and build nightly container
#2270
dsikka
closed
6 months ago
0
Bump jinja2 from 3.0.1 to 3.1.4 in /research/information_retrieval/doc2query
#2269
dependabot[bot]
opened
6 months ago
0
[MOE Quantization] Update transformers version to 4.40.0
#2268
dbogunowicz
closed
6 months ago
1
Bump tqdm from 4.61.1 to 4.66.3 in /research/information_retrieval/doc2query
#2267
dependabot[bot]
opened
6 months ago
0
Split `Wanda` and `SparseGPT`
#2266
rahul-tuli
closed
6 months ago
0
Fixing GHA Hangs
#2265
Satrat
closed
6 months ago
1
Fix GSM template
#2264
anmarques
closed
6 months ago
0
[Feature Branch] Quant modifier UX
#2263
rahul-tuli
closed
6 months ago
0
[MOE Quantization] Warn against "undercalibrated" modules
#2262
dbogunowicz
opened
6 months ago
0
Move Session Management to Top Level
#2261
Satrat
closed
6 months ago
1
Quantization Compressor Support
#2260
Satrat
closed
6 months ago
6
Allow torch 2.3 and remove torch ceiling version restriction
#2259
mgoin
closed
6 months ago
2
Missing key(s) in state_dict: "model.0.conv.quant.activation_post_process.scale"
#2258
thijsgelton
closed
6 months ago
5
Fix markdown links
#2257
dbogunowicz
closed
7 months ago
1
Previous
Next