issues
search
neuralmagic
/
deepsparse
Sparsity-aware deep learning inference runtime for CPUs
https://neuralmagic.com/deepsparse/
Other
2.97k
stars
171
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
[Pipeline Refactor][Text Generation][Continuous Batching] Integration
#1409
dsikka
closed
9 months ago
1
[BugFix] Redefine ARG between stages
#1408
rahul-tuli
closed
10 months ago
0
[Cherry-Pick][Fix][Text Generation Pipeline] Fix the erroneous sampling logic
#1407
dbogunowicz
closed
10 months ago
0
[Fix][Text Generation Pipeline] Fix the erroneous sampling logic
#1406
dbogunowicz
closed
10 months ago
1
[Test][Text Generation Pipeline] Add a lightweight integration tests (uses `TinyStories-1M`)
#1405
dbogunowicz
closed
10 months ago
0
[yolov8] readme fixes
#1404
bfineran
closed
10 months ago
0
[Text Generation][V2][Fix] Properly digest `max_new_tokens` argument
#1403
dbogunowicz
closed
9 months ago
0
[Text Generation][V2] End-to-end tests
#1402
dbogunowicz
closed
9 months ago
0
[cherry-pick 1.6][bugfix] set config path correctly after deployment dir download (#1396)
#1401
bfineran
closed
10 months ago
0
[Cherry Pick] [Fix] Remove erronous LIB.kv_cache input when using external kv cache management
#1400
dbogunowicz
closed
10 months ago
0
[Cherry Pick] Refactor of perplexity computation
#1399
dbogunowicz
closed
10 months ago
0
[WIP][Text Generation][V2] Streaming
#1398
dbogunowicz
closed
9 months ago
1
transformers_embedding-extraction for text-generation tasks
#1397
BDHU
closed
8 months ago
3
[bugfix] set config path correctly after deployment dir download
#1396
bfineran
closed
10 months ago
0
Timer Middleware Hardcoded
#1395
horheynm
closed
9 months ago
0
[Pipeline Refactor][Text-Generation] Refactor `transformers` helpers functions
#1394
dbogunowicz
closed
9 months ago
2
[Evaluator] Implementation of `CLI`
#1393
dbogunowicz
closed
10 months ago
0
[Pipeline Refactor] Unit Testing for Text Generation Operators
#1392
dsikka
closed
10 months ago
0
[continuous batching] singleton pattern for scheduler
#1391
bfineran
closed
10 months ago
0
[Evaluator] Implementation of `Evaluation` (output schema for `evaluation` module)
#1390
dbogunowicz
closed
10 months ago
0
Update sentence_transformers/README.md for benchmarking
#1389
mgoin
closed
10 months ago
0
[Evaluator] Implementation of `EvaluationRegistry`
#1388
dbogunowicz
closed
10 months ago
1
[Evaluator] Implementation of `lm-evaluation-harness` integration
#1387
dbogunowicz
closed
10 months ago
0
[Evaluator][Feature Branch] Implementation of `evaluate` function
#1386
dbogunowicz
closed
9 months ago
0
Add python 3.11 to test-check.yaml
#1385
mgoin
closed
10 months ago
1
[Pipeline Refactor] Split/Join Functionality for multiple prompts
#1384
dsikka
closed
10 months ago
0
[Evaluator] Implementation of `lm-evaluation-harness` integration
#1383
dbogunowicz
closed
10 months ago
0
[Evaluator] Blueprint
#1382
dbogunowicz
closed
10 months ago
0
[Pipeline Refactor] split/join
#1381
dsikka
closed
10 months ago
0
[Pipeline Refactor] async
#1380
dsikka
closed
9 months ago
3
Update sentence_transformer.py with batched padding
#1379
mgoin
closed
10 months ago
0
Add hf: stub support to model_to_path
#1378
mgoin
closed
10 months ago
0
[Fix] The benchmark logic when internal kv cache is involved
#1377
dbogunowicz
closed
10 months ago
0
[Cherry Pick] Enable preparing nested OutputSchemas for serialization (#1357)
#1376
dbogunowicz
closed
10 months ago
0
[ContinuousBatching] ContinuousBatchingScheduler Implementation
#1375
bfineran
closed
10 months ago
2
[Continuous Batching] Executor thread for running continuous batching
#1374
bfineran
closed
10 months ago
0
[Continuous Batching] Queue Implementation to support batching grouping and prioritization
#1373
bfineran
closed
10 months ago
0
Assertion `!cache_sizes.empty()' failed
#1372
akarym-sl
closed
10 months ago
2
[v2] EngineOperator updates to make continuous batching easier
#1371
bfineran
closed
10 months ago
0
[Pipeline Refactor][Text-Generation] Simplify `DecoderKVCache`
#1370
dbogunowicz
closed
9 months ago
1
Research: 4-bit quantization
#1369
truenorth8
closed
4 months ago
5
update datasets version
#1368
Satrat
closed
10 months ago
0
Add straggler log to debug from onnx.py
#1367
mgoin
closed
10 months ago
0
Update openai.md config
#1366
mgoin
closed
10 months ago
0
[Pipeline Refactor][Text-Generation][No KV Cache Pipeline] Prepare scaffolding for no-kv cache pipeline
#1365
dbogunowicz
closed
10 months ago
0
[Pipeline Refactor][Text-Generation] Create a helper function for creating engine_inputs
#1364
dbogunowicz
closed
10 months ago
1
[WiP] Working on few improvements for v2 LLM pipeline
#1363
dbogunowicz
closed
10 months ago
0
Updated Contributors Section in readme.md
#1362
mohitd404
closed
10 months ago
0
Adding Contributors Section to readme.md
#1361
mohitd404
closed
10 months ago
1
https://www.therapyinsightspractice.com
#1360
Mjsmiles23
closed
10 months ago
1
Previous
Next