HappyZ happyz
0 Followers · 0 Following
Repositories
18
 Projects Packages Public Activity Starred Repositories
happyz synced commits to refs/pull/18892/merge at happyz/llama.cpp from mirror 2026-02-24 18:01:40 -08:00
ee2665fe9d Merge 979299a32f into 47eb12b953
47eb12b953 server: fix query params lost when proxying requests in multi-model router mode (#19854)
418dea39ce ggml/gguf : prevent integer overflows (#19856)
da426cb250 model : update label for LFM2-24B-A2B (#19848)
c830f99cfa server : support max_completion_tokens request property (#19831)
Compare 24 commits »
happyz synced commits to refs/pull/18923/merge at happyz/llama.cpp from mirror 2026-02-24 18:01:40 -08:00
ade271420e Merge 7f14ce6344 into 47eb12b953
47eb12b953 server: fix query params lost when proxying requests in multi-model router mode (#19854)
418dea39ce ggml/gguf : prevent integer overflows (#19856)
da426cb250 model : update label for LFM2-24B-A2B (#19848)
c830f99cfa server : support max_completion_tokens request property (#19831)
Compare 24 commits »
happyz synced commits to refs/pull/18858/merge at happyz/llama.cpp from mirror 2026-02-24 18:01:39 -08:00
c558ab8cc3 Merge a73b9d361a into 47eb12b953
47eb12b953 server: fix query params lost when proxying requests in multi-model router mode (#19854)
418dea39ce ggml/gguf : prevent integer overflows (#19856)
da426cb250 model : update label for LFM2-24B-A2B (#19848)
c830f99cfa server : support max_completion_tokens request property (#19831)
Compare 8 commits »
happyz synced commits to refs/pull/18861/merge at happyz/llama.cpp from mirror 2026-02-24 18:01:39 -08:00
508841a454 Merge 35d10cbab6 into 47eb12b953
47eb12b953 server: fix query params lost when proxying requests in multi-model router mode (#19854)
418dea39ce ggml/gguf : prevent integer overflows (#19856)
da426cb250 model : update label for LFM2-24B-A2B (#19848)
c830f99cfa server : support max_completion_tokens request property (#19831)
Compare 24 commits »
happyz synced commits to refs/pull/18872/merge at happyz/llama.cpp from mirror 2026-02-24 18:01:39 -08:00
704e3001e6 Merge d57f289264 into 47eb12b953
47eb12b953 server: fix query params lost when proxying requests in multi-model router mode (#19854)
418dea39ce ggml/gguf : prevent integer overflows (#19856)
da426cb250 model : update label for LFM2-24B-A2B (#19848)
c830f99cfa server : support max_completion_tokens request property (#19831)
Compare 34 commits »
happyz synced commits to refs/pull/18879/merge at happyz/llama.cpp from mirror 2026-02-24 18:01:39 -08:00
6b5c26a267 Merge 16c4aba272 into 47eb12b953
47eb12b953 server: fix query params lost when proxying requests in multi-model router mode (#19854)
418dea39ce ggml/gguf : prevent integer overflows (#19856)
da426cb250 model : update label for LFM2-24B-A2B (#19848)
c830f99cfa server : support max_completion_tokens request property (#19831)
Compare 29 commits »
happyz synced commits to refs/pull/18886/merge at happyz/llama.cpp from mirror 2026-02-24 18:01:39 -08:00
15e4b7ded1 Merge fc36eb7700 into 418dea39ce
418dea39ce ggml/gguf : prevent integer overflows (#19856)
da426cb250 model : update label for LFM2-24B-A2B (#19848)
c830f99cfa server : support max_completion_tokens request property (#19831)
aa6f918c1c Vulkan Scalar Flash Attention Refactor (#19625)
Compare 7 commits »
happyz synced commits to refs/pull/18816/merge at happyz/llama.cpp from mirror 2026-02-24 18:01:38 -08:00
4f6e70b2f7 Merge 6cf18ecd6b into 244641955f
244641955f models : fix graph splits (#19866)
47eb12b953 server: fix query params lost when proxying requests in multi-model router mode (#19854)
418dea39ce ggml/gguf : prevent integer overflows (#19856)
da426cb250 model : update label for LFM2-24B-A2B (#19848)
Compare 5 commits »
happyz synced commits to refs/pull/18817/merge at happyz/llama.cpp from mirror 2026-02-24 18:01:38 -08:00
f7bd052194 Merge f45ba0d0ef into 47eb12b953
47eb12b953 server: fix query params lost when proxying requests in multi-model router mode (#19854)
418dea39ce ggml/gguf : prevent integer overflows (#19856)
da426cb250 model : update label for LFM2-24B-A2B (#19848)
c830f99cfa server : support max_completion_tokens request property (#19831)
Compare 34 commits »
happyz synced commits to refs/pull/18836/merge at happyz/llama.cpp from mirror 2026-02-24 18:01:38 -08:00
0ab718c666 Merge 39137bfe63 into 47eb12b953
47eb12b953 server: fix query params lost when proxying requests in multi-model router mode (#19854)
418dea39ce ggml/gguf : prevent integer overflows (#19856)
da426cb250 model : update label for LFM2-24B-A2B (#19848)
c830f99cfa server : support max_completion_tokens request property (#19831)
Compare 27 commits »
happyz synced commits to refs/pull/18851/merge at happyz/llama.cpp from mirror 2026-02-24 18:01:38 -08:00
01762afe46 Merge 3829263010 into 47eb12b953
47eb12b953 server: fix query params lost when proxying requests in multi-model router mode (#19854)
418dea39ce ggml/gguf : prevent integer overflows (#19856)
da426cb250 model : update label for LFM2-24B-A2B (#19848)
c830f99cfa server : support max_completion_tokens request property (#19831)
Compare 24 commits »
happyz synced commits to refs/pull/18711/merge at happyz/llama.cpp from mirror 2026-02-24 18:01:37 -08:00
b910079479 Merge e45a3b354e into 47eb12b953
47eb12b953 server: fix query params lost when proxying requests in multi-model router mode (#19854)
418dea39ce ggml/gguf : prevent integer overflows (#19856)
da426cb250 model : update label for LFM2-24B-A2B (#19848)
c830f99cfa server : support max_completion_tokens request property (#19831)
Compare 6 commits »
happyz synced commits to refs/pull/18742/merge at happyz/llama.cpp from mirror 2026-02-24 18:01:37 -08:00
1639d03054 Merge 9882f21ab9 into 47eb12b953
47eb12b953 server: fix query params lost when proxying requests in multi-model router mode (#19854)
418dea39ce ggml/gguf : prevent integer overflows (#19856)
da426cb250 model : update label for LFM2-24B-A2B (#19848)
c830f99cfa server : support max_completion_tokens request property (#19831)
Compare 11 commits »
happyz synced commits to refs/pull/18745/merge at happyz/llama.cpp from mirror 2026-02-24 18:01:37 -08:00
d33e6a61e9 Merge d7ec22fe46 into 47eb12b953
47eb12b953 server: fix query params lost when proxying requests in multi-model router mode (#19854)
418dea39ce ggml/gguf : prevent integer overflows (#19856)
da426cb250 model : update label for LFM2-24B-A2B (#19848)
c830f99cfa server : support max_completion_tokens request property (#19831)
Compare 23 commits »
happyz synced commits to refs/pull/18750/merge at happyz/llama.cpp from mirror 2026-02-24 18:01:37 -08:00
fc9e40549f Merge 8bcd53b74e into 47eb12b953
47eb12b953 server: fix query params lost when proxying requests in multi-model router mode (#19854)
418dea39ce ggml/gguf : prevent integer overflows (#19856)
da426cb250 model : update label for LFM2-24B-A2B (#19848)
c830f99cfa server : support max_completion_tokens request property (#19831)
Compare 33 commits »
happyz synced commits to refs/pull/18576/merge at happyz/llama.cpp from mirror 2026-02-24 18:01:36 -08:00
37716e6d23 Merge 74dbb2eef2 into 47eb12b953
47eb12b953 server: fix query params lost when proxying requests in multi-model router mode (#19854)
418dea39ce ggml/gguf : prevent integer overflows (#19856)
da426cb250 model : update label for LFM2-24B-A2B (#19848)
c830f99cfa server : support max_completion_tokens request property (#19831)
Compare 11 commits »
happyz synced commits to refs/pull/18626/merge at happyz/llama.cpp from mirror 2026-02-24 18:01:36 -08:00
5993220fb1 Merge 9eec24ad8a into 47eb12b953
47eb12b953 server: fix query params lost when proxying requests in multi-model router mode (#19854)
418dea39ce ggml/gguf : prevent integer overflows (#19856)
da426cb250 model : update label for LFM2-24B-A2B (#19848)
c830f99cfa server : support max_completion_tokens request property (#19831)
Compare 8 commits »
happyz synced commits to refs/pull/18633/merge at happyz/llama.cpp from mirror 2026-02-24 18:01:36 -08:00
eb8d4a4c80 Merge 1f0d90c3dd into 47eb12b953
47eb12b953 server: fix query params lost when proxying requests in multi-model router mode (#19854)
418dea39ce ggml/gguf : prevent integer overflows (#19856)
da426cb250 model : update label for LFM2-24B-A2B (#19848)
c830f99cfa server : support max_completion_tokens request property (#19831)
Compare 29 commits »
happyz synced commits to refs/pull/18698/merge at happyz/llama.cpp from mirror 2026-02-24 18:01:36 -08:00
5670ba79d6 Merge 07e9a39c6e into 47eb12b953
47eb12b953 server: fix query params lost when proxying requests in multi-model router mode (#19854)
418dea39ce ggml/gguf : prevent integer overflows (#19856)
da426cb250 model : update label for LFM2-24B-A2B (#19848)
c830f99cfa server : support max_completion_tokens request property (#19831)
Compare 33 commits »
happyz synced commits to refs/pull/18059/merge at happyz/llama.cpp from mirror 2026-02-24 18:01:35 -08:00
baa56f9bd0 Merge fde17e0f5d into da426cb250
fde17e0f5d webui: Client-side implementation of tool calling with calculator tool and (javascript) code interpreter tool
da426cb250 model : update label for LFM2-24B-A2B (#19848)
c830f99cfa server : support max_completion_tokens request property (#19831)
aa6f918c1c Vulkan Scalar Flash Attention Refactor (#19625)
Compare 10 commits »