llama.cpp

flake.lock: Update

#996:Commit bc80c85018 pushed by root

update_flake_lock_action

2024-11-11 06:10:33 +00:00

0s

ggml : add ggml-cpu.h to the public headers (#10204)

#958:Commit 97404c4a03 pushed by root

master

2024-11-09 00:10:33 +00:00

0s

convert : fix flake8 lint

#920:Commit b4e9c5998d pushed by root

compilade/mamba2

2024-11-06 06:10:33 +00:00

0s

flake.lock: Update

#881:Commit 1855a062a2 pushed by root

update_flake_lock_action

2024-11-04 03:36:17 +00:00

0s

server : fix slot selection by lru (#10126)

#868:Commit 42cadc74bd pushed by root

master

2024-11-03 21:36:17 +00:00

0s

ggml : fix memory leaks when loading invalid gguf files (#10094)

#811:Commit b9e02e8184 pushed by root

master

2024-10-31 21:36:17 +00:00

0s

server : don't overfill the batch during infill

#768:Commit 48d5a1f8d0 pushed by root

gg/infill-6

2024-10-29 03:36:17 +00:00

0s

flake.lock: Update

#764:Commit ac031c2ac4 pushed by root

update_flake_lock_action

2024-10-28 09:36:17 +00:00

0s

server : check that the prompt fits in the slot's context (#10030)

#750:Commit bc5ba007b2 pushed by root

b3975

2024-10-26 15:36:17 +00:00

0s

llamafile : extend sgemm.cpp support for Q5_0 models (#10010)

#747:Commit 2f8bd2b901 pushed by root

master

2024-10-26 15:36:17 +00:00

0s

server : check that the prompt fits in the slot's context

#726:Commit 1905ba1a22 pushed by root

gg/server-check-ctx

2024-10-25 15:36:17 +00:00

0s

Rwkv chat template fix (#10001)

#699:Commit 11d47057a5 pushed by root

b3960

2024-10-23 21:36:17 +00:00

0s

llama : fix empty batch causing llama_batch_allocr to crash (#9966)

#696:Commit c8c07d658a pushed by root

master

2024-10-23 21:36:17 +00:00

0s

llama : add chat template for RWKV-World + fix EOT (#9968)

#690:Commit 4ff7fe1fb3 pushed by root

b3958

2024-10-23 15:36:17 +00:00

0s

lora : warn user if new token is added in the adapter (#9948)

#686:Commit c421ac072d pushed by root

master

2024-10-22 19:56:21 +00:00

0s

llama-bench : add time-to-first-byte stat

#646:Commit bc82fc2ed8 pushed by root

gg/ttfb

2024-10-19 21:36:17 +00:00

0s

graph-prof: fix compilation error on ubuntu

#591:Commit e7e9a7fca8 pushed by root

graph-profiler

2024-10-17 09:36:17 +00:00

0s

add amx kernel for gemm

#537:Commit fc709cfc96 pushed by root

pr_add_intel_amx_support

2024-10-12 15:36:17 +00:00

0s

flake.lock: Update

#469:Commit f5c35c109c pushed by root

update_flake_lock_action

2024-10-07 09:36:17 +00:00

0s

Update ggml/src/ggml-backend-impl.h

#394:Commit 805fea97ac pushed by root

sl/backend-registry-2

2024-10-02 21:36:17 +00:00

0s

Merge branch 'master' into compilade/mamba2

#387:Commit 7d6cb36895 pushed by root

compilade/mamba2

2024-10-02 21:36:17 +00:00

0s

llama : print correct model type for Llama 3.2 1B and 3B

#382:Commit a90484c6d9 pushed by root

master

2024-10-02 09:36:17 +00:00

0s

metal : add comments

#377:Commit 5273e59b09 pushed by root

gg/perf-metal

2024-10-02 09:36:17 +00:00

0s

ggml-backend : add device and backend reg interfaces

#373:Commit 7166ad4136 pushed by root

sl/backend-registry-2

2024-10-01 17:36:22 +00:00

0s

Merge branch 'master' into compilade/convert-merges-pairs-to-old

#363:Commit a38fc04f4d pushed by root

compilade/convert-merges-pairs-to-old

2024-10-02 03:36:17 +00:00

0s

py : update transfomers version (#9694)

#357:Commit 08a43d05b6 pushed by root

master

2024-10-01 09:26:19 +00:00

0s

common : ensure llama_batch size does not exceed max size (#9668)

#338:Commit faac0bae26 pushed by root

master

2024-09-30 17:06:21 +00:00

0s

llama : add support for Chameleon (#8543)

#326:Commit 9a913110cf pushed by root

b3834

2024-09-29 21:36:17 +00:00

0s

test-backend-ops : use flops for some performance tests

#306:Commit d4c57cd641 pushed by root

sl/test-backend-ops-perf-flops

2024-09-28 03:36:17 +00:00

0s

ci : add rerank tests

#297:Commit f19554f453 pushed by root

gg/rerank

2024-09-27 15:36:17 +00:00

0s