root
0 Followers · 0 Following
  • Joined on 2024-09-10
Repositories
5
 Projects Packages Public Activity Starred Repositories
root synced new reference refs/tags/b4000 to root/llama.cpp from mirror 2024-11-01 08:36:21 +00:00
root synced commits to refs/tags/b4001 at root/llama.cpp from mirror 2024-11-01 08:36:21 +00:00
root synced new reference refs/tags/b4001 to root/llama.cpp from mirror 2024-11-01 08:36:21 +00:00
root synced commits to refs/tags/b4002 at root/llama.cpp from mirror 2024-11-01 08:36:21 +00:00
root synced and deleted reference refs/tags/refs/pull/10107/merge at root/llama.cpp from mirror 2024-11-01 08:36:20 +00:00
root synced commits to gg/idle at root/llama.cpp from mirror 2024-11-01 08:36:20 +00:00
root synced new reference gg/idle to root/llama.cpp from mirror 2024-11-01 08:36:20 +00:00
root synced commits to master at root/llama.cpp from mirror 2024-11-01 08:36:20 +00:00
815fe72adc sync : ggml
f221d56220 ggml : alloc ggml_contexts on the heap (whisper/2525)
e597e50794 build: fix build error in Windows env with OneAPI setup (#10107)
Compare 3 commits »
root synced commits to sl/ggml-cpp-wrappers at root/llama.cpp from mirror 2024-11-01 08:36:20 +00:00
root synced new reference sl/ggml-cpp-wrappers to root/llama.cpp from mirror 2024-11-01 08:36:20 +00:00
root synced commits to refs/pull/10004/merge at root/llama.cpp from mirror 2024-11-01 08:36:20 +00:00
be24c8ec6c Merge 8ceda95327 into 85679d37f3
85679d37f3 llama : improve output buffer type selection (#10098)
1e9f94994e quantize : fix --keep-split (#10114)
Compare 3 commits »
root synced commits to refs/pull/10008/merge at root/llama.cpp from mirror 2024-11-01 08:36:20 +00:00
7a77786991 Merge a279f17815 into 815fe72adc
815fe72adc sync : ggml
f221d56220 ggml : alloc ggml_contexts on the heap (whisper/2525)
e597e50794 build: fix build error in Windows env with OneAPI setup (#10107)
85679d37f3 llama : improve output buffer type selection (#10098)
Compare 6 commits »
root synced commits to refs/pull/10041/merge at root/llama.cpp from mirror 2024-11-01 08:36:20 +00:00
eb5baa72bc Merge 449717f1b0 into 85679d37f3
85679d37f3 llama : improve output buffer type selection (#10098)
1e9f94994e quantize : fix --keep-split (#10114)
c02e5ab2a6 llama : fix buffer checks for mamba and rwk (#10111)
ab3d71f97f loader: refactor tensor weights storage (#9935)
Compare 8 commits »
root synced commits to refs/pull/10044/merge at root/llama.cpp from mirror 2024-11-01 08:36:20 +00:00
cabdf4475d Merge fcc5a22fde into 85679d37f3
85679d37f3 llama : improve output buffer type selection (#10098)
1e9f94994e quantize : fix --keep-split (#10114)
c02e5ab2a6 llama : fix buffer checks for mamba and rwk (#10111)
Compare 4 commits »
root synced commits to refs/pull/10048/head at root/llama.cpp from mirror 2024-11-01 08:36:20 +00:00
2b7be22977 Merge branch 'ggerganov:master' into k-shift2
e597e50794 build: fix build error in Windows env with OneAPI setup (#10107)
85679d37f3 llama : improve output buffer type selection (#10098)
1e9f94994e quantize : fix --keep-split (#10114)
c02e5ab2a6 llama : fix buffer checks for mamba and rwk (#10111)
Compare 9 commits »
root synced commits to refs/pull/10048/merge at root/llama.cpp from mirror 2024-11-01 08:36:20 +00:00
a3104545cb Merge 2b7be22977 into e597e50794
2b7be22977 Merge branch 'ggerganov:master' into k-shift2
e597e50794 build: fix build error in Windows env with OneAPI setup (#10107)
Compare 3 commits »
root synced commits to refs/pull/10053/merge at root/llama.cpp from mirror 2024-11-01 08:36:20 +00:00
ed2c667267 Merge 006167dd65 into e597e50794
e597e50794 build: fix build error in Windows env with OneAPI setup (#10107)
85679d37f3 llama : improve output buffer type selection (#10098)
1e9f94994e quantize : fix --keep-split (#10114)
c02e5ab2a6 llama : fix buffer checks for mamba and rwk (#10111)
Compare 6 commits »
root synced commits to refs/pull/10055/merge at root/llama.cpp from mirror 2024-11-01 08:36:20 +00:00
ba7ba8e44a Merge be84bb973e into e597e50794
e597e50794 build: fix build error in Windows env with OneAPI setup (#10107)
Compare 2 commits »
root synced commits to refs/pull/9930/merge at root/llama.cpp from mirror 2024-11-01 00:26:22 +00:00
5c213d5ed1 Merge 630bce5a7f into 0a683e8088
0a683e8088 server : include scheme when printing URL (#10106)
dea5e86051 ggml : check tensor name lengths in gguf files (#10100)
1329c0a75e kompute: add mul_mat_q4_k shader (#10097)
Compare 4 commits »
root synced commits to refs/pull/9935/head at root/llama.cpp from mirror 2024-11-01 00:26:22 +00:00
9a99293174 use sorted map, sort weights by layer
13eba91a32 minor style changes
0a683e8088 server : include scheme when printing URL (#10106)
dea5e86051 ggml : check tensor name lengths in gguf files (#10100)
1329c0a75e kompute: add mul_mat_q4_k shader (#10097)
Compare 5 commits »