🦙
🦙
I like big .vimrc and I cannot lie
- Sofia, Bulgaria
-
18:47
(UTC +02:00) - https://ggerganov.com
- @ggerganov
Sponsors
Block or Report
Block or report ggerganov
Report abuse
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abusePinned
-
-
wave-share
wave-share PublicServerless, peer-to-peer, local file sharing through sound
3,857 contributions in the last year
Day of Week | April Apr | May May | June Jun | July Jul | August Aug | September Sep | October Oct | November Nov | December Dec | January Jan | February Feb | March Mar | |||||||||||||||||||||||||||||||||||||||||
Sunday Sun | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Monday Mon | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Tuesday Tue | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Wednesday Wed | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Thursday Thu | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Friday Fri | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Saturday Sat |
Less
No contributions.
Low contributions.
Medium-low contributions.
Medium-high contributions.
High contributions.
More
Contribution activity
March 2024
Created 174 commits in 4 repositories
Created a pull request in ggerganov/llama.cpp that received 25 comments
server : refactor
ref #4216
Moved the code around to logically similar things closer together and did some renaming. The cache_tokens
management should be improved -…
+2,265
−2,711
lines changed
•
25
comments
Opened 46 other pull requests in 5 repositories
ggerganov/llama.cpp
2
open
34
merged
-
sync : ggml
This contribution was made on Mar 27
-
imatrix : fix wname for mul_mat_id ops
This contribution was made on Mar 24
-
nix: update flake.lock
This contribution was made on Mar 24
-
common : add HF arg helpers
This contribution was made on Mar 22
-
server : enable continuous batching by default
This contribution was made on Mar 22
-
metal : proper assert for mat-mat memory alignment
This contribution was made on Mar 22
-
tests : disable system() calls
This contribution was made on Mar 21
-
metal : pad n_ctx by 32
This contribution was made on Mar 20
-
ci : temporary disable sanitizer builds
This contribution was made on Mar 18
-
common : disable repeat penalties by default
This contribution was made on Mar 18
-
ci : disable stale issue messages
This contribution was made on Mar 18
-
ci : close all stale issues at once
This contribution was made on Mar 17
-
nix: update flake.lock
This contribution was made on Mar 17
-
llama : fix integer overflow during quantization
This contribution was made on Mar 14
-
ggml : designate enum vals for integer types
This contribution was made on Mar 14
-
metal : build metallib + fix embed path
This contribution was made on Mar 12
-
ggml : fix UB in IQ2_S and IQ3_S
This contribution was made on Mar 12
-
sycl : try to fix SYCL after IQ1_S changes
This contribution was made on Mar 11
-
llama : more consistent names of count variables
This contribution was made on Mar 11
-
llama : refactor unicode stuff
This contribution was made on Mar 11
-
metal : move mm_id indices to shared mem
This contribution was made on Mar 10
-
nix: update flake.lock
This contribution was made on Mar 10
-
server : fix metrics init
This contribution was made on Mar 9
-
server : clarify some items in the readme
This contribution was made on Mar 9
-
server : simplify logic for empty prompts
This contribution was made on Mar 9
- Some pull requests not shown.
ggerganov/whisper.cpp
4
merged
1
closed
-
sync : ggml
This contribution was made on Mar 27
-
whisper : improve handling of prompts
This contribution was made on Mar 21
-
ruby : fix build
This contribution was made on Mar 20
-
whisper : allocate encoder results in dedicated buffer
This contribution was made on Mar 16
-
ggml : try fix 32-bit arm compat
This contribution was made on Mar 8
ggerganov/ggml
3
merged
-
sync : llama.cpp
This contribution was made on Mar 27
-
spec : add GGUF diagram
This contribution was made on Mar 15
-
sync : llama.cpp
This contribution was made on Mar 14
NousResearch/nous-llama.cpp
1
merged
-
control-vectors : minor code style updates
This contribution was made on Mar 14
pacman100/llama.cpp
1
merged
-
starcoder2 : change rope type to neox
This contribution was made on Mar 1
Reviewed 187 pull requests in 5 repositories
ggerganov/llama.cpp
25 pull requests
-
llama : fix command-r inference when omitting outputs
This contribution was made on Mar 28
-
ci: bench: fix master not schedule, fix commit status failed on external repo
This contribution was made on Mar 28
-
Fixed some MobileVLM's inference bugs. Added more tests on different devices.
This contribution was made on Mar 28
-
llama : save and restore kv cache for single seq id
This contribution was made on Mar 28
-
convert : refactor vocab selection logic
This contribution was made on Mar 28
-
nix: ci: dont test cuda and rocm (for now)
This contribution was made on Mar 27
-
server: continuous performance monitoring and PR comment
This contribution was made on Mar 27
-
embedding : show full embedding for single prompt
This contribution was made on Mar 27
-
[SYCL] Fix batched impl for NVidia GPU
This contribution was made on Mar 27
-
[Model] Add support for xverse
This contribution was made on Mar 27
-
Change --no-penalize-nl to --penalize-nl
This contribution was made on Mar 27
-
Make tokenize CLI tool have nicer command line arguments.
This contribution was made on Mar 27
-
Make IQ1_M work for QK_K = 64
This contribution was made on Mar 27
-
add php api bindings to readme
This contribution was made on Mar 27
-
quantize: be able to override metadata by key
This contribution was made on Mar 26
-
IQ1_M: 1.75 bpw quantization
This contribution was made on Mar 26
-
[convert-hf] Fix exception in sentencepiece with added tokens
This contribution was made on Mar 26
-
embedding: adjust
n_ubatch
value, print error on insufficientn_batch
valueThis contribution was made on Mar 26 -
server : add
n_discard
parameter to specify the number of tokens to discard when context is shiftedThis contribution was made on Mar 26 -
wpm : portable unicode tolower
This contribution was made on Mar 26
-
llama : greatly reduce output buffer memory usage
This contribution was made on Mar 26
-
Include IQ2_XXS and IQ2_XS in test-quantize-fns
This contribution was made on Mar 25
-
cuda : rename build flag to LLAMA_CUDA
This contribution was made on Mar 25
-
cuda : fix LLAMA_CUDA_F16 build
This contribution was made on Mar 25
-
add
retrieval
exampleThis contribution was made on Mar 25 - Some pull request reviews not shown.
ggerganov/whisper.cpp
18 pull requests
-
ci : add building in MSYS2 environments (Windows)
This contribution was made on Mar 28
-
Use pkg-config for OpenBLAS
This contribution was made on Mar 28
-
Implemented command-style grammar in the main example.
This contribution was made on Mar 28
-
Allow a regular expression to describe tokens to suppress
This contribution was made on Mar 28
-
Improve support for distil-large-v3
This contribution was made on Mar 21
-
libcuda.so.1 in PATH in Docker Container
This contribution was made on Mar 20
-
Fedora dependencies needed (SDL2)
This contribution was made on Mar 20
-
[DRAFT] Token level timestamps with DTW (#375)
This contribution was made on Mar 20
-
Rename --audio-context to --audio-ctx, as per help text
This contribution was made on Mar 18
-
whisper : allocate encoder results in dedicated buffer
This contribution was made on Mar 16
-
whisper : document whisper_batch.n_seq_id
This contribution was made on Mar 10
-
whisper : improve beam search candidate diversity
This contribution was made on Mar 10
-
bindings/go : add linker flags to make metal work
This contribution was made on Mar 9
-
whisper : make beam candidate sort more stable
This contribution was made on Mar 9
-
Fix typo in source file whisper.cpp
This contribution was made on Mar 5
-
Fix SF(segment fault) issue in Android JNI
This contribution was made on Mar 5
-
Add library versioning
This contribution was made on Mar 4
-
Update README to Recommend MacOS Sonoma for Core ML to avoid hallucination
This contribution was made on Mar 4
ggerganov/ggml
6 pull requests
-
Update GGUF docs
This contribution was made on Mar 27
-
Update CMakeLists.txt
This contribution was made on Mar 22
-
Fix examples/simple/simple-ctx
This contribution was made on Mar 22
-
gguf : add Mamba keys and tensors
This contribution was made on Mar 13
-
ggml_status introduction
This contribution was made on Mar 4
-
add some new ops, fix some operators and add batch operations to certain operators.
This contribution was made on Mar 3
huggingface/huggingface.js
2 pull requests
-
GGUF parser: support big-endian files
This contribution was made on Mar 12
-
a GGUF parser that works on remotely hosted files (over HTTP range requests)
This contribution was made on Mar 12
ggml-org/ci
1 pull request
-
ci: add install-docker.sh
This contribution was made on Mar 25
Created an issue in ggerganov/llama.cpp that received 4 comments
llama : add Deepseek support
Creating this issue for more visibility The main problem is around tokenization support, since the models use some variation of the BPE pre-process…
4
comments
Opened 3 other issues in 2 repositories
ggerganov/llama.cpp
2
open
-
ci : re-enable sanitizer builds when they work again
This contribution was made on Mar 18
-
llama : combine expert tensors into a single tensor
This contribution was made on Mar 15
ggerganov/whisper.cpp
1
closed
-
whisper : adapt to latest ggml changes
This contribution was made on Mar 15
Answered 3 discussions in 1 repository
ggerganov/llama.cpp
ggerganov/llama.cpp
-
Shouldn't prompt formats be an enumerator?
This contribution was made on Mar 27
-
Why is the forward pass compute for transpose a no-op?
This contribution was made on Mar 22
-
Is llama.cpp designed to be consumed via CLI or C programs?
This contribution was made on Mar 10