issues
search
google
/
gemma.cpp
lightweight, standalone C++ inference engine for Google's Gemma models.
Apache License 2.0
5.75k
stars
487
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Update gemma_test with the expected entropy values for the IT models of size 2B/7B/9B/27B.
#294
copybara-service[bot]
closed
2 hours ago
0
Move benchmark_helper to evals/, weights_raw to compression/.
#293
copybara-service[bot]
opened
3 hours ago
0
Fix handling of %c and %q if eot_string. Fixes #283, thanks @ljcucc
#292
copybara-service[bot]
closed
3 hours ago
0
Cleanup: move util/compress and convert_weights to compression/
#291
copybara-service[bot]
closed
7 hours ago
0
Add Py bindings for weight compression
#290
copybara-service[bot]
closed
10 hours ago
0
Fix gemma_test - moved to evals/.
#289
copybara-service[bot]
closed
1 day ago
0
7x compile time speedup: shard gemma.cc
#288
copybara-service[bot]
closed
2 days ago
0
Add configurables for norm/rope/activation/scale/residual connection.
#287
copybara-service[bot]
opened
2 days ago
0
Small cleanups. Fixes gemma_test build.
#286
copybara-service[bot]
closed
2 days ago
0
Prep for sharding gemma.cc: split into kv_cache, tokenizer.
#284
copybara-service[bot]
closed
3 days ago
0
The %C and %Q will not detected when eot_line = "other string"
#283
ljcucc
opened
3 days ago
1
Use benchmark_helper in py bindings (adds BOS)
#282
copybara-service[bot]
closed
3 days ago
0
Cleanup: add ModelInfo struct, remove gcpp::
#281
copybara-service[bot]
closed
3 days ago
0
Add sliding window attention for Gemma 2.
#280
copybara-service[bot]
closed
3 days ago
1
Add config for att/final cap, skip max-subtract. Fixes #278
#279
copybara-service[bot]
closed
4 days ago
0
low quality responses from gemma.cpp (gemma-2-27b) when compared to AIstudio and others
#278
matteoserva
closed
4 days ago
3
Declutter gemma/ directory, move binaries to evals/ and util/.
#277
copybara-service[bot]
closed
4 days ago
0
There is an extra `<end_of_turn>\n` in the output
#276
ufownl
opened
1 week ago
1
Remove unused kSystemPrompt
#275
copybara-service[bot]
closed
4 days ago
0
Introduce new Gemma 9B and 27B configs
#274
copybara-service[bot]
closed
1 week ago
0
Refactor model type / training tables, simplify reverse mapping
#273
copybara-service[bot]
closed
1 week ago
0
Remove unused BUILD dependency
#272
copybara-service[bot]
closed
1 week ago
0
Fix a clang tidy warning
#271
copybara-service[bot]
closed
1 week ago
1
Improve logging when running Gemma examples: fix the issue when max_tokens, max_generated_tokens and temperature were logging without any trailing space/newline.
#270
copybara-service[bot]
closed
1 week ago
1
Add prompt batching to Gemma.cpp.
#269
copybara-service[bot]
closed
4 days ago
1
Skip the last RMSNormInplaceBatched in the Prefill phase.
#268
copybara-service[bot]
closed
2 weeks ago
1
Fix compilation errors in clang
#267
ufownl
closed
2 weeks ago
1
Fix KV cache size calculation error
#266
ufownl
closed
2 weeks ago
0
Fixing two typos.
#265
copybara-service[bot]
closed
2 weeks ago
0
Code cleanup
#264
copybara-service[bot]
closed
2 weeks ago
0
Move test placeholder to a later pos.
#263
copybara-service[bot]
closed
2 weeks ago
1
Refactor kCachePosSize and kCacheLayerSize into separate functors.
#262
copybara-service[bot]
closed
2 weeks ago
1
Split out common parts (embedder and transformer block) from Prefill() and Transformer() into separate functions.
#261
copybara-service[bot]
closed
2 weeks ago
1
Move kGriffinLayers into ConfigNoSSM, set kGemmaLayers directly
#260
copybara-service[bot]
closed
2 weeks ago
0
Fix debug_prompt and other binaries (internal init)
#259
copybara-service[bot]
closed
2 weeks ago
0
Simplify Attention.
#258
copybara-service[bot]
closed
2 weeks ago
0
Fix Py binding/run_example: use GemmaEnv
#257
copybara-service[bot]
closed
2 weeks ago
0
1.15x 7b sfp prefill speedup: Matmul in attention
#256
copybara-service[bot]
closed
2 weeks ago
0
Update developer docs and mention asan/msan
#255
copybara-service[bot]
closed
2 weeks ago
0
Further simplification to ForEachTensor, thanks I.K.
#254
copybara-service[bot]
closed
2 weeks ago
0
Fix DASSERT - TiledBatch requires at least 2 vectors.
#253
copybara-service[bot]
closed
2 weeks ago
0
RecurrentGemma 9b support
#252
fizzAI
opened
2 weeks ago
1
Use hwy::ThreadPool::MaxThreads() to determine the number of threads to use.
#251
copybara-service[bot]
closed
1 week ago
1
docs: update README.md
#250
eltociear
opened
3 weeks ago
0
Move raw_weights into separate header, used mainly by compress_weights.
#249
copybara-service[bot]
closed
2 weeks ago
0
Refactor CompressedWeights.
#248
copybara-service[bot]
closed
2 weeks ago
1
Added bias vector addition to MatMul
#247
copybara-service[bot]
closed
3 weeks ago
0
Removed now redundant non-batch matmul
#246
copybara-service[bot]
closed
3 weeks ago
0
Implement a missing (bf16, f32) tiled MatMul kernel.
#245
copybara-service[bot]
closed
3 weeks ago
0
Internal change.
#244
copybara-service[bot]
closed
3 weeks ago
1
Next